Slide 1: ARTIFICIAL INTELLIGENCE CONTENTS :CONTENTS INTRODUCTION TO A.I. EVOLUTION OF A.I. BRANCHES OF A.I. APPLICATIONS OF A.I. CONCLUSIONS ON A.I.

INTRODUCTION :INTRODUCTION WHAT IS A.I. ? A.I. is a branch of computer science that studies the computational requirements for tasks such as perception, reasoning and learning and develop systems to perform those tasks The field of Artificial intelligence strives to understand and build intelligent entities A.I. Strong A.I. M/C can think and act like human Weak A.I. Some thinking like features can be added to M/C Slide 4:INTRODUCTION TURING TEST * Intelligence is defined as the ability to achieve human level performance in all cognitive tests, sufficient to fool a human interrogator. * The test was devised in response to the question, Can a computer think ?. * Result was +ve if interrogator can not tell if responses are coming from the M/C or Human. * Proposed by Alan Turing(1950), a British Computer Scientist. Slide 5:INTRODUCTION TURING TEST One person sits at a computer and types the questions. The computer is connected to two other hidden computers At one computer, Human reads and responds to questions. At the other end, computer with no Human aid runs the program to provide responses. Slide 6:INTRODUCTION DEFINITIONS * AI is a branch of computer science dealing with symbolic, nonalgorithmic methods of problem solving * AI is a branch of computer science that deals with ways of knowledge using symbols rather than numbers and with Heuristics, method for processing information. * AI works with pattern matching methods which attempt to describe objects , events or processes in terms of their qualitative features and logical and computational Relationship. Slide 7:INTRODUCTION What is Intelligence ? To respond to situations very flexibly. To make sense out of ambiguous or contradictory messages. To recognize the relative importance of different elements of situations To find similarities between situations despite difference To draw distinctions between situations despite similarities which may link them. Slide 8:HISTORY 1943 McCulloh and Pitts, Boolean circuit model of brain. 1950 Turings computing machine and intelligence. 1950s Early AI programs including Samuels checker program, Newell and Simons logic theorist, Gelisnters geometry engine 1956 Dartmouth conference.

Slide 9:HISTORY 1952-69 Look, Ma, no hands! era. 1958 McCarthy moves to MIT, LISP was born. 1965 Robinsons complete algorithm for logical reasoning. 196674 AI discovers computational complex. Neural network research almost disappears. 1969-79 - Early development in knowledge based systems. Slide 10:HISTORY 1980-88 : Expert system industry booms. 1988-93 : Expert system industry busts. 1985-88 : Neural networks return to popularity. 1995 : Agents Agents Agents. (present) BRANCHES :BRANCHES Logical AI What a program knows about the world in general the facts of the specific situation in which it must act and its goal are all represented by sentences of some mathematical logical language. Pattern Recognition When a program makes observation of some kind, it is often programmed to compare what it sees with already stored patterns. BRANCHES :BRANCHES Representation Facts about the world have to be represented in some way. Usually languages of mathematical logic are used. Common Sense, Knowledge and Reasoning This is an era in which AI is farthest from human level. While there has been considerable progress, e.g. in development systems of non monotonic reasoning and theories of action BRANCHES :BRANCHES Planning Planning programs start with general facts about the world. They generate a strategy for achieving the goal, the strategy is just a sequence of action. Epistemology This is a study of the kinds of knowledge that are required for solving problems in the world. Ontology It is the study of kinds of things that exist. In AI, things deal with various kinds of object. BRANCHES :BRANCHES Heuristics Heuristics is a way of trying to discover something or an idea embedded in a program. It predicates that compare two nodes in a search tree to see if one is better than other, e.I. constitutes an advance towards the goal, may be more useful. Genetic Engineering It is a technique for getting programs to solve a task by mating random LISP programs and selecting fittest in millions of generations. APPLICATIONS OF A.I. :APPLICATIONS OF A.I. Expert systems. Natural Language Processing (NLP). Speech recognition. Computer vision. Robotics. Automatic Programming.

APPLICATIONS :APPLICATIONS EXPERT SYSTEMS An Expert System is a computer program designed to act as an expert in a particular domain (area of expertise). Expert systems currently are designed to assist experts, not to replace them, They have been used in medical diagnosis, chemical analysis, geological explorations etc. Domain of E.S. Knowledge base Facts Heuristics Phases in Expert System APPLICATIONS :APPLICATIONS Speech Recognition The primary interactive method of communication used by humans is not reading and writing, it is speech. The goal of speech recognition research is to allow computers to understand human speech. So that they can hear our voices and recognize the words we are speaking. It simplifies the process of interactive communication between people and computers, thus it advances the goal of NLP. APPLICATIONS :APPLICATIONS Natural Language Processing The goal of NLP is to enable people and computers to communicate in a natural (humanly) language(such as, English) rather than in a computer language. The field of NLP is divided in 2 categories Natural Language understanding. Natural Language generation. APPLICATIONS :APPLICATIONS Computer Vision People generally use vision as their primary means of sensing their environment, we generally see more than we hear, feel or smell or taste. The goal of computer vision research is to give computers this same powerful facility for understanding their surrounding. Here AI helps computer to understand what they see through attached cameras. APPLICATIONS :APPLICATIONS Robotics A Robot is a electro-mechanical device that can by programmed to perform manual tasks or a reprogrammable multi functional manipulator designed to move materials, parts, tools, or specialized devices through variable programmed motions for performance of variety of tasks. An intelligent robot includes some kind of sensory apparatus that allows it to respond to change in its environment. Slide 21:APPLICATIONS Robotics APPLICATIONS :APPLICATIONS Automatic Programming Programming is a process of telling a computer exactly what you want it to do.Writing a program is a tedious job. It must be designed, written, tested, debugged and evaluated. The goal of automatic planning is to create special programs that act intelligent tools to assist programmers and expedite each phase of programming process. Ultimate aim is computer itself should develop a program in accordance with specifications of programmer.

FUTURE :FUTURE The day is not far when you will just sit back in your cozy little beds and just command your personal Robot's to entirely do your ruts . He will be a perfect companion for you. Just enjoy the Technology. FUTURE :FUTURE But wait, dont be happy. It may end in other way too. Some day there will be a knock to your door. As you open it, you see a large number of Robots marching into your house destroying everything you own and looting you. This is because ever since there is an advantage in the Technology, it attracts anti-social elements. This is true for Robots too. Because now they will have full power to think as human, even as of anti-social elements. So think trice before giving them power of Cognition. CONCLUSION :CONCLUSION In its short existence, AI has increased understanding of the nature of intelligence and provided an impressive array of application in a wide range of areas. It has sharpened understanding of human reasoning, and of the nature of intelligence in general. At the same time, it has revealed the complexity of modeling human reasoning providing new areas and rich challenges for the future. Tumour Markers: Present and Future: Tumour Markers: Present and Future Eleftherios P. Diamandis, M.D., Ph.D., FRCP(C) Dept. of Pathology & Laboratory Medicine, Mount Sinai Hospital Dept. of Laboratory Medicine & Pathobiology, University of Toronto, Toronto, Canada The New Cancer Diagnostics : The New Cancer Diagnostics We Need: We Need better (more objective) and more biologically-relevant tumor classification schemes for prognosis, selection of therapy better tumor markers for population screening and early diagnosis Paradigm Shift (2000 and Beyond): Paradigm Shift (2000 and Beyond) Traditional Method: Study one molecule at a time. New Method: Multiparametric analysis (thousands of molecules at a time). Cancer: Does every cancer have a unique fingerprint? (genomic/proteomic?) Changes are Coming: Changes are Coming Changes seen are driven by recent biological / technological advances: Human Genome Project Bioinformatics Array Analysis (DNA; proteins; tissues) Mass Spectrometry Automated DNA Sequencing /PCR Laser Capture Microdissection SNPs Comparative Genomic Hybridization

Technological Advances: Technological Advances Microarrays: Microarrays What is a microarray? A microarray is a compact device that contains a large number of well-defined immobilized capture molecules (e.g. synthetic oligos, PCR products, proteins, antibodies) assembled in an addressable format. You can expose an unknown (test) substance on it and then examine where the molecule was captured. You can then derive information on identity and amount of captured molecule. Slide8: Science 2004; 306: 630-631 Slide9: Microscope slide DNA microarray Slide10: Cy3-dUTP green fluorescent reverse transcriptase, T7 RNA polymerase Cy5dUTP red fluorescent cRNA cRNA RNA extraction and labeling to determine expression level sample of interest compared to standard reference Microarray Milestone: June 2003 : Microarray Milestone: June 2003 Following their papers in Nature and NEJM Nature 2002; 415: 530-536 NEJM 2002; 347: 1999-2009 Vant Veer and colleagues (Netherlands Cancer Institute) will use microarray profiling as a routine tool for breast cancer management (administration of adjuvant chemotherapy after surgery). prospective trials under way; EORTC; 2005 onwards Applications of Microarrays: Applications of Microarrays Simultaneous study of gene expression patterns of genes Single nucleotide polymorphism (SNP) detection Sequences by hybridization / genotyping / mutation detection Study protein expression (multianalyte assay) Protein-protein interactions Provides: Massive parallel information Slide14: Microarrays, such as Affymetrixs GeneChip, now include all 50,000 known human genes. Science, 302: 211, 10 October, 2003 Comparative Genomic Hybridization: Comparative Genomic Hybridization A method of comparing differences in DNA copy number between tests (e.g. tumor) and reference samples Can use paraffin-embedded tissues Good method for identifying gene amplifications or deletions by scanning the whole genome. Comparative Genomic Hybridization: Comparative Genomic Hybridization Label with

Cy-3 Label with Cy-5 Cot1DNA blocks repeats) Nature Reviews Cancer 2001;1:151-157 Arrayed CGH: Arrayed CGH Same as previous slide but use arrays of BAC clones instead of chromosomes Laser Capture Microdissection: Laser Capture Microdissection An inverted microscope with a low intensity laser that allows the precise capture of single or defined cell groups from frozen or paraffin-embedded histological sections Allows working with welldefined clinical material. Tumor Heterogeneity (Prostate Cancer): Tumor Heterogeneity (Prostate Cancer) Tumor Cells: Red Benign Glands: Blue Rubin MA J Pathol 2001;195;80-86 Laser Capture Microdissection: Laser Capture Microdissection LCM uses a laser beam and a special thermoplastic polymer transfer cup (A).The cap is set on the surface of the tissue and a laser pulse is sent through the transparent cap,expanding the thermoplastic polymer. The selected cells are now adherent to the transfer cap and can be lifted off the tissue and placed directly onto an eppendorf tube for extraction (B). Rubin MA, J Pathol 2001;195:80-86 Tissue Microarray: Tissue Microarray Printing on a slide tiny amounts of tissue Array many patients in one slide (e.g. 500) Process all at once (e.g. immunohistochemistry) Works with archival tissue (paraffin blocks) Gene Expression Analysis of Tumors: Gene Expression Analysis of Tumors cDNA Microarray Lakhani and Ashworth Nature Reviews Cancer 2001;1:151-157 Tissue Microarray: Tissue Microarray From Jacquemier1 et al Cancer Res 2005;65:767779 Molecular Profiling of Prostate Cancer: Molecular Profiling of Prostate Cancer Rubin MA, J Pathol 2001;195:80-86 Single Nucleotide Polymorphisms (SNPs): Single Nucleotide Polymorphisms (SNPs) DNA variation at one base pair level; found at a frequency of 1 SNP per 1,000 - 2,000 bases A map of 9 x 106 SNPs have been described in humans by the International SNP map working group (HapMap) 60,000 SNPs fall within exons; the rest are in introns

Why Are SNPs Useful?: Why Are SNPs Useful? Human genetic diversity depends on SNPs between individuals (these are our genetic differences!) Specific combinations of alleles (called The Haplotype) seem to play a major role in our genetic diversity How does this genotype affect the phenotype Disease Disposition? Haplotype Patterns: Haplotype Patterns Person A A T T G A T C G G A T. . . C C A T C G G A . . . C T A A Person B A T T G A T A G G A T. . . C C A G C G G A . . . C T C A Person C A T T G A T C G G A T. . . C C A T C G G A . . . C T A A Person E A T T G A T C G G A T. . . C C A T C G G A . . . C T A A Person D A T T G A T A G G A T. . . C C A G C G G A . . . C T C A Persons B and D share a haplotype unlike the other three, characterized by three different SNPs. Science, 2002; 296: 1391-1393. Why Are SNPs Useful?: Why Are SNPs Useful? Diagnostic Application Determine somebodys haplotype (sets of SNPs) and assess disease risk. Be careful: These diseaserelated haplotypes are not as yet known! SNP Analysis by Microarray: SNP Analysis by Microarray GeneChip HuSNPTM Mapping Assay (Affymetrix) More than 100,000 single nucleotide polymorphisms (SNPs) covering all 22 autosomes and the X chromosome in a single experiment Coverage: 1 SNP per 20 kb of DNA Needs: 250 ng of genomic DNA-1 PCR reaction Commercial Microarray for Clinical Use (Pharmacogenomics): Commercial Microarray for Clinical Use (Pharmacogenomics) Roche Product CYP 450 Genotyping (drug metabolizing system) First FDA approved microarray-based diagnostic test; 2004 Proteomics & Protein Microarrays: Proteomics & Protein Microarrays Slide32: High-throughput proteomic analysis Haab et al. Genome Biology 2000;1:1-22 Protein array now commercially available from BD Biosciences (2002) Applications of Protein Microarrays : Applications of Protein Microarrays Screening for: Small molecule targets Post-translational modifications Protein-protein interactions Protein-DNA interactions Enzyme assays Epitope mapping Cytokine Specific Microarray ELISA: BIOTINYLATED MAB CAPTURE MAB ANTIGEN Detection system Cytokine Specific Microarray ELISA

Recently Published Examples: Recently Published Examples Rationale For Improved Subclassification of Cancer by Microarray Analysis: Rationale For Improved Subclassification of Cancer by Microarray Analysis Classically classified tumors are clinically very heterogeneous some respond very well to chemotherapy; some do not. Hypothesis: Hypothesis The phenotypic diversity of cancer might be accompanied by a corresponding diversity in gene expression patterns that can be captured by using cDNA microarray Then Systematic investigation of gene expression patterns in human tumors Molecularmight provide the basis of an improved taxonomy of cancer portraits of cancer Molecular signatures Molecular Portraits of Cancer: Molecular Portraits of Cancer Breast Cancer Perou et al. Nature 2000;406:747-752 Green: Underexpression Black: Equal expression Red: Overexpression Left Panel: Cell Lines Right Panel: Breast Tumors Figure Represents 1753 Genes Differential Diagnosis of Childhood Malignancies: Differential Diagnosis of Childhood Malignancies Ewing Sarcoma: Yellow Rhabdomyosarcoma: Red Burkitt Lymphoma: Blue Neuroblastoma: Green Khan et al. Nature Medicine 2001;7:673-679 Applications (continued) Vantt Veer L. et al. Nature 2002:415-586: Applications (continued) Vantt Veer L. et al. Nature 2002:415-586 Examine lymph node negative breast cancer patients and identified specific signatures for: Poor prognosis BRCA carriers The poor prognosis signature consisted of genes regulating cell cycle invasion, metastasis and angiogenesis. Conclusion This gene expression profile will outperform all currently-used clinical parameters in predicting disease outcome This may be a good strategy to select nodenegative patients who would benefit from adjuvant therapy. Validation of prognosis signature: Validation of prognosis signature performance on unselected consecutive series at 10 years (n=295) Lymph node negative patients (n=151) Lymph node positive patients (n=144) <53 yrs, tumor <5cm, no prior malignancy predictive value compared to classical clinical parameters relevance for treatment tailoring Vant Veer et al New Engl J Med 2002;347:1999-2009

Slide42: Cohort of 295 tumors patients < 53 yrs, lymph node negative or positive Unselected consecutive patient series, mean follow-up ~ 7 yrs 295 tumors 70 prognosis genes Kaplan-Meier survival curves for all 295 patients: Kaplan-Meier survival curves for all 295 patients Slide44: premenopausal, lymph node negative Treatment tailoring by profiling Therapeutic implications: Therapeutic implications Who to treat: Prognosis profile as diagnostic tool improvement of accurate selection for adjuvant therapy (less under- and overtreatment) Prognosis profile implemented in clinical trials reduction in number of patients & costs (select only patients that are at metastases risk) How to treat: Predictive profile for drug response selection of patients who benefit Commercial Products: Commercial Products Oncotype DX by Genomic Health Inc, Redwood City, CA A prognostic test for breast cancer metastasis based on profiling 250 genes; 16 genes as a group have predictive value; $3,400 per test 215,000 breast cancer cases per year (potential market value > $500 million!) Test has no value for predicting response to treatment Am J Pathol 2004;164:35-42 Commercial Products: Commercial Products Mammaprint marketed by Agendia, Amsterdam, The Netherlands Based on L.Vant Veer publications Test costs Euro 1650; based on 70 gene signature Prospective trials underway Celera and Arcturus developing similar tests (prognosis/prediction of therapy) Science 2004;303:1754-5 Mass Spectrometry for Proteomic Pattern Generation: Mass Spectrometry for Proteomic Pattern Generation Serum analysis by SELDI-TOF mass spectrometry after extraction of lower molecular weight proteins Data analyzed by a pattern recognition algorithm ProteinChip Arrays: SELDI affinity chip surfaces (Ciphergen): ProteinChip Arrays: SELDI affinity chip surfaces (Ciphergen) Reverse Phase Anionic Cationic IMAC Normal Phase Slide50: Proteins are captured, retained and purified directly on the chip (affinity capture ) Laser The SELDI Process and ProteinChip Arrays Sample goes directly onto

the ProteinChip Array Surface is read by Surface-Enhanced Laser Desorption/Ionization (SELDI) ProteinChip Array Slide51: Detector Laser Flight Tube Mass Spectrometry-Based Proteomics and Bioinformatics The Future of Biomarkers m/z Relative Intensity Target Results: Ovarian Cancer: Results: Ovarian Cancer Petricoin III EF, et al. Lancet 2002;359:572-577 Slide53: Diamandis, EP J Natl Cancer Inst 2004; 96: 353-356 Reviews / Opinions / Commentaries Diamandis, EP Clin Chem 2003; 49: 1272-1275 Diamandis, EP Mol Cell Proteomics 2004; 3:367-78 Microarray discrepancies (185 genes): Microarray discrepancies (185 genes) Science 2004; 306: 630-631 Prediction of cancer outcome with microarrays: a multiple random validation strategy: Michiels et al. Lancet, 2005; 365: 488-492. Prediction of cancer outcome with microarrays: a multiple random validation strategy Description of eligible studies : Description of eligible studies Microarrays & molecular research: noise discovery?: Microarrays & molecular research: noise discovery? In 5 of the 7 largest studies on cancer prognosis, this technology performs no better than flipping a coin. The other two studies barely beat horoscopes J.P. Ioannides Lancet 2005; 365: 454-455 Prediction of cancer outcome with microarrays: a multiple random validation strategy: Prediction of cancer outcome with microarrays: a multiple random validation strategy Findings: The list of genes identified as predictors of prognosis was highly unstable; molecular signatures strongly depended on the selection of patients in the training sets Michiels et al. Lancet, 2005; 365: 488-492. Prediction of cancer outcome with microarrays: a multiple random validation strategy: Findings: Because of inadequate validation, our chosen studies published overoptimistic results compared with those from our own analyses. Michiels et al.

Lancet, 2005; 365: 488-492. Prediction of cancer outcome with microarrays: a multiple random validation strategy The Future??: Imaging Multiparametric/miniature testing of serum on a protein array Mass spectrometric serum/urine proteomic pattern generation The Future?? The Future??: Asymptomatic individuals Predisposition to certain disease Prevention (drugs; lifestyle) Surveillance Whole genome SNP analysis The Future?? The Future??: The Future?? Cancer patient Cancerous tissue Tumour fingerprint Individualized treatment Surgery / Biopsy Array analysis Different Types of Robots: Different Types of Robots Robot Arms (Fixed Robots) Mobile Robots Humanoid Robots Legged Robots Wheel Robots 3 wheels 2 Driver wheels, 1 Caster 1 Driver wheel, 2 Casters 4 wheels Casters make diverse problems in the control of the robot Wheel Robot Main Components: Wheel Robot Main Components Main Components Mechanics Wheels Driver Motor (s) Power Transmission System Electronics Controller Board Needing feedback from environment Sensors We are now discussing some of the above topics Different Types of Motors: Different Types of Motors DC Motors You can simply control it AC Motors Its difficult to be controlled but it can be used in high power applications Servo Motors You have complete control on the shaft angle Different Types of Feed Back: Different Types of Feed Back Sensors IR Sensors Pressure Sensors Light Sensors Temperature Sensors Encoder What is Encoder: What is Encoder Why do we use Power Transmission Systems?: Why do we use Power Transmission Systems? To reduce Angular Velocity To increase Torque P = (T . w) = cte. Different Transmission Systems Gear Hard manufacturing and adjustment Pulley So w => T Gear: Gear Gears are used to change the speed and force of the motor. You can use gears to: Speed up or slow down your robot. Make your robot stronger or weaker. There are many different types of gears Spur Gear Bevel Gear Worm Gear Rack & Pinion

Gear: Gear Spur gears are wheels with teeth Gear: Gear Bevel gears mesh at right angles, so they change the direction of rotation. Gear: Gear Worm gears look like screws. They have many special properties. Gear: Gear Rack & pinion gears turn rotational motion into straight-line motion. Slide12: Where does all this torque come from? Consider a pair of gears that are meshed together. F t The moment arm is the radius of the gear. Remember: t = F x r r A torque on this axle... produces a force at the tooth. Slide13: F t r The force from the small gears tooth pushes against the large gears tooth. This creates an equal (and opposite) force in the large gear. This is Newtons 3rd Law. and produces a larger torque on this axle. The force acts through this larger moment arm... Slide14: Analyzing the forces... t1 = F1 x r1 t2 = F2 x r2 F1 = t1 / r1 F2 = t2 / r2 F1 = F2 t1 / r1 = -t2 / r2 -t2 / t1 = r2 / r1 The ratio of torques is the ratio of the gear radii. This is the gear ratio! Idler Gear: Idler Gear An idler gear is a gear that is inserted between two other gears. Idler gears do not affect the gear ratio between the input and output gears. The gear ratio would be computed just the same if there were no idler gear. Idler Gear: Idler Gear Recall that when using spur gears, the output axle rotates in the opposite direction as the input axle. You can also use idler gears to change the spacing between the input and output axles Remember, idler gears do not change the gear ratio Gear: Gear The gear ratio of this gear box is 75 to 1 That means the last axle rotates 75 times slower than the first axle. It also means the last axle has 75 times the torque as the first axle. Slide18: Try this experiment. Have one person turn this wheel. And have another person

try to hold on to this wheel. Slide19: Gears can increase the torque (and force) that they exert on something. This is known as mechanical advantage. BUT, it comes at a price. Do you know what it is? torque increases Slide20: Belt Drives Uses friction to transmit power Velocity Ratio: D1.w1=D2.w2 Belt Drive Basics: Belt Drive Basics Motor Nameplate Size DR DN Belt Drive Basics: Belt Drive Basics 700 rpm 4375 rpm Ratio always greater than 1 Speed Ratio = 2.5 How to assemble our Robot: How to assemble our Robot Here is our package How to assemble our Robot: How to assemble our Robot 1 2 3 How to assemble our Robot: How to assemble our Robot Bottom view of the robot How to assemble our Robot: How to assemble our Robot Sensor board assembly If you have any further help please contact us at:: If you have any further help please contact us at: robot@schoolnet.ir Please take a look at our website at: Robot.schoolnet.ir

Slide 1:Ch. 7: Assessment of Intelligence Slide 2:Brief, Brief History of Intelligence Testing Concept of Intelligence The IQ meaning and correlates Clinical Assessment of Intelligence major instruments and issues Ch. 7 Overview: Assessment of Intelligence

Slide 3:Historical Developments Leading to IQ Testing Alfred Binet/Theodore Simon and the Educational need for IQ testing Psychological science increasingly demonstrates mental abilities can be measured with IQ tests. Legal/Civil Rights Arena Fairness of IQ testing for diverse populations Brief, Brief History of Intelligence Testing Slide 4:When Intelligence Testing Goes Wrong http://www.youtube.com/watch?v=gYZtcTxWf4U Slide 5:Differences ability, aptitude, & achievement. No universally accepted definition of intelligence Common references for defining intelligence - adjustment/adaptation to new environments - ability to learn/educability - abstract thinking Definitions of Intelligence Slide 6:Interactive Intelligence Test http://www.youtube.com/watch?v=pRBcosUeE_0 Slide 7:David Wechslers Definition of Intelligence Intelligence is the aggregate or global capacity of the individual to act purposefully, to think rationally and to deal effectively with his

environment. - Global because it characterizes individuals behavior as a whole - Aggregate because it is composed of elements or abilities that are qualitatively differentiable Slide 8:David Wechslers Definition of Intelligence http://www.youtube.com/watch?v=ONwiuiZ6mJ0 Slide 9:Factor Analytic Approaches Spearman g and s factors - L.L. Thurstone 7 group factors R.B. Cattell g, 17-primary factors, 2 2nd factors fluid and crystallized abilities - J.J. Guilford 3 intelligence components operations, contents, and products Approaches/Theories of Intelligence Slide 10:Theoretical Approaches H. Gardner: Theory of Multiple Intelligences (families of 6 intelligences) http://www.youtube.com/watch? v=KEFpaY3GI-I&feature=related Slide 11:Theoretical Approaches H. Gardner: Theory of Multiple Intelligences (families of 6 intelligences) Slide 12:- R. Sternberg Triarchic Theory (3: componential [analytical], experiential [creative

thinking], contextual [practical street smarts]) Approaches/Theories of Intelligence Slide 13:Time to Assess Your IQ whatever that means http://www.youtube.com/watch? v=ZgZkNwfjPvw Slide 14:Cracker Barrel IQ Test-III-R Slide 15:Binet (MA: Mental Age) Stern (IQ: Mental Age/Chronological Age x 100) The Intelligent Quotient (IQ): Its Meaning and Development Slide 16:Weshsler (Deviation IQ) The Intelligent Quotient (IQ): Its Meaning and Development Slide 17:The Intelligent Quotient (IQ): Empirical Correlates Slide 18:School Success (IQ & grades r = .50) Occupational Success (best for job entry) Group Differences? Influence of Heredity on IQ scores (5181%) Stability of IQ scores The Intelligent Quotient (IQ): Empirical Correlates

Slide 19:Standford-Binet Scales - descriptions, standardization, reliability/validity Types of Modern IQ Tests Slide 21:Wechsler Scales - Adults (WAIS-III/IV) Children (WISC-IV) Types of Modern IQ Tests Slide 22:Structure of the Scale WAISIII Levels of Performance FSIQ Digit Span Arithmetic Letter Number Sequencing Vocabulary Similarities Information Comprehension Digit SymbolCoding Symbol Search Block Design Matrix Reasoning Picture Completion Picture Arrangement VIQ PIQ VCI WMI POI PSI 8 Slide 25:Estimation of General Intelligence Level Prediction of Academic Success Appraisal of Style and Abstraction Role of the Situation Generality vs. Specificity of Measurement Issues in Clinical Use of Intelligence Tests Artificial Intelligence :1 Artificial Intelligence CSC 4601 List of Books :2 List of Books Artificial Intelligence (A modern Approach), 2nd Edition, by Stuart Russell and Peter Norvig. Artificial Intelligence, 3rd

Edition, Winston. Artificial Intelligence : Structures and Strategies for Complex Problem Solving, 5th Edition, George Luger. Artificial Intelligence, Elaine Rich and Kevin Knight. Chapters (List of Contents) :3 Chapters (List of Contents) 1 Introduction 2 Problem Solving 3 Genetic Algorithms 4 Knowledge Representation and Reasoning 5 Expert Systems 6 Handling uncertainty with fuzzy systems 7 Introduction to learning 8 Planning 9 Advanced Topics 10 Conclusion 1.1 What is intelligence? :4 1.1 What is intelligence? The ability of problem solving demonstrates intelligence Example-1 Consider a mouse trying to search/reach the piece of cheese placed at right top corner of the image. This problem can be considered as a common real life problem which we deal with many times in our life, i.e. finding a path, may be to a university, to a friends house, to a market, or in this case to the piece of cheese. The mouse tries various paths as shown by arrows and can reach the cheese by more than one path. In other words the mouse can find more than one solutions to this problem. We can say that the mouse is intelligent enough to find a solution to the problem. Hence the ability of problem solving demonstrates intelligence.

Slide 5:5 1.1 What is intelligence?... Example-2 Biological example of Intelligence and AI How insects apply Rosenblatts/Hebbian Learning ? Slide 6:6 1.1 What is intelligence?... Biological example of Intelligence and AI How insects apply Rosenblatts/Hebbian Learning ? 1.1 What is intelligence?... :7 1.1 What is intelligence?... The Capabilities like thinking, memory manipulation (storing, recalling), numerical processing, and decision making come in intelligence. Example-3: Find the next number in the sequence given below: 1, 4, 9, 16, The next number is obviously 25 but is achieved through thinking, memory recalling, numerical processing, and decision making. When we try to solve something, we check various ways to solve it, we check different combinations, and many other things to solve different problems. 1.1 What is intelligence :8 1.1 What is intelligence Example-4 A doctor checks a patient The doctor collects some knowledge about the patient by asking some questions and measuring temperature (T), Blood Pressure (BP), Pulse Rate

(PR) etc. Then based on his previous knowledge he tries to diagnose the disease. His previous knowledge is based on rules like: If the patient has a high BP and normal T and normal PR then he is not well. Diagnosing a disease has many other complex information and observations involved, we have just mentioned a very simple case here. It is important to consider here that a doctor who would have a better memory to store all this precious knowledge, better ability of retrieving the correct portion of the knowledge for the correct patient, will be better able to classify a patient. Hence, telling us that good memory, good recall, and efficient memory and information manipulation also comes in intelligence. 1.1 What is intelligence :9 Example-5: Ambiguous and fuzzy problems demonstrates intelligence Things are not so simple. Moreover, people dont think in the same manner. Are you short, medium or tall? You might think that you are tall but your friend who is taller than you might say that NO! You are not. Some people might think that the people around 4ft are short, around 5ft are medium, and around 6ft are tall. Others might say that the people around 4.5ft are short, around 5.5ft are medium and around 6.5ft are tall. Even having the same measurements, different people can get completely different results because they approach the problem in different fashions. Things can be

even more complex when the same person, having observed same measurements and solves the same problem in two different ways and reaches different solutions. We all know that we answer such fuzzy questions very efficiently in our daily lives. Our intelligence actually helps us to do this. Hence the ability to tackle ambiguous and fuzzy problems demonstrates intelligence. 1.1 What is intelligence

1.2 Intelligent Machines :10 1.2 Intelligent Machines A machine is intelligent if It can find a path by searching through a mesh. It can solve problems like the next number in the sequence. It can develop plans/schedule like a time-table. It can diagnose and prescribe, like a doctor. It can answers ambiguous questions. It can recognizes fingerprints, faces, and optical character. It can understands. It can perceives knowledge. It can get trained. It can upgrade its previous learning. Preferably, It should be general purpose and multitasking having. It should have distributed and parallel architecture. In short, we wish it to behave like human! A machine having such properties is called an intelligent machine. But do you think this is the real natural intelligence?. Answer is No; Not at all. Instead this is Artificial intelligence. 1.3 Formal Definitions of AI :11 1.3 Formal

Definitions of AI The exciting new effort to make computers think machines with minds, in the full and literal sense (Haugeland, 1985). [The automation of] activities that we associate with human thinking, activities such as decision making, problem solving, learning (Bellman, 1978). The study of mental faculties through the use of computational models (Charniak and McDermott). The study of computation that make it possible to perceive reason and act (Winston 1992). The art of creating machines that perform functions that require intelligence when performed by people (Kurzweil 1990). The study of how to make computers do things at which, at the moment, people are better (Rich and Knight, 1991). A field of study that seeks to explain and emulate intelligent behavior in terms of computational processes (Schalkoff, 1990). The branch of computer science that is concerned with the automation of intelligent behavior (Luger and Stubblefield, 1993). 1.3 Formal Definitions of AI :12 1.3 Formal Definitions of AI Thinking Humanly To make computers think like human we need a way of determining how human think. For this we need to get inside the actual functioning of the human mind. There are two ways to do this: (i) through introspection - trying to catch out our own thoughts as they go by. And (ii) through psychological experiments: that concern with the activities of

brain. Once we have a precise theory of mind, it becomes possible to express the theory as a computer program that follows the same rules. The interdisciplinary field of cognitive science brings together computer models from AI and experimental techniques from psychology to try to construct precise and testable theories of the working of human mind. 1.3 Formal Definitions of AI :13 1.3 Formal Definitions of AI Acting Humanly The issue of acting like human comes up when AI programs have to do something physically which human usually do in real life. For instance, when a natural language processing system makes a dialog with a person, or when some intelligent software gives out a medical diagnosis, or when a robotic arm sorts out manufactured goods coming over a conveyer belt. Keeping in view all the above motivations, let us give a fairly comprehensive comment that Artificial Intelligence is a field which deals with the study and development of systems that can perceive, learn, think, analyze and act like a real human. 1.4 History and Evolution of AI :14 1.4 History and Evolution of AI AI is a young field. It has inherited its ideas, concepts and techniques from many disciplines like biology, psychology, philosophy, linguistics, mathematics, etc. From philosophy, we

have theories of reasoning and learning . From mathematics, we have formal theories of logic, probability, decision-making, and computation. From psychology, we have the tools and techniques to investigate the human mind and ways to represent the resulting theories. Linguistics provides us with the theories of structure and meaning of language. From biology we have information about the network structure of human brain and all the theories on functionalities of different human organs. Finally from computer science we have tools and concepts to make AI a reality. 1.4.1 First recognized work on AI :15 1.4.1 First recognized work on AI The first work that is now generally recognized as AI was done by Warren McCulloch and Walter Pitts (1943). They proposed a neuron model. They showed that the neuron is a bi-state element i.e. on or off and that the state of the neuron is the response of sufficient stimulation by a number of neighboring neurons. They claimed (without providing an evidence) that any logical task can be performed by suitably connecting a sufficient number of neurons. but they didnt pursued this idea much at that time. Donald Hebb (1949) demonstrated a simple updating rule (training method) for modifying the connection strengths (weights) between neurons such that learning could take place.

1.4.2 The name of the field as Artificial Intelligence : 16 1.4.2 The name of the field as Artificial Intelligence In 1956 some of the U.S researchers got together and organized a two-month workshop at Dartmouth. There were altogether only 10 attendees. Allen Newell and Herbert Simon actually dominated the workshop. Although all the researchers had some excellent ideas and a few even had some demo programs like checkers, but Newell and Herbert already had a reasoning program, the Logic Theorist. The program came up with proofs for logic theorems. The most lasting and memorable thing that came out of that workshop was an agreement to adopt the new name for the field: Artificial Intelligence. Over the next twenty years these people, their students and colleagues at MIT, CMU, Stanford and IBM, dominated the field of artificial intelligence. 1.4.3 First program that thought humanly :17 1.4.3 First program that thought humanly In the early years AI met drastic success. The researchers were highly motivated to try out AI techniques to solve problems that were not yet been solved. Many of them met great successes. Newell and Simons early success was followed up with the General Problem Solver. Unlike Logic Theorist, this program was developed in the manner that it attacked a problem imitating the steps that human take when solving a

problem. Though it was catered for a limited class of problems but it was found out that it addressed those problems in a way very similar to that as human. It was probably the first program that imitated human thinking approach. 1.4.4 Development of Lisp :18 1.4.4 Development of Lisp In 1958 In MIT AI Lab, McCarthy defined the high-level language Lisp that became the dominant AI programming language in the proceeding years. Though McCarthy had the required tools with him to implement programs in this language but access to scarce and expensive computing resources were also a serious problem. Thus he and other researchers at MIT invented time sharing. Also in 1958 he published a paper titled Programs with Common Sense. This Program can be seen as the first complete AI system. Unlike the other systems at that time, it was to cater general knowledge of the world. For example, he showed that how some simple rules could help a program generate a plan to drive to an airport and catch the plane. 1.5 Applications :19 1.5 Applications Artificial finds its application in a lot of areas. A few of the applications will be mentioned here. Many information retrieval systems like Google search engine uses artificially intelligent crawlers and content based searching techniques to efficiency and

accuracy of the information retrieval. A lot of computer based games like chess, 3D combat games use intelligent software to make the user feel as if the machine on which that game is running were intelligent. Computer Vision is a new area where people are trying to develop the sense of visionary perception into a machine. Natural language processing is another area which tries to make machines speak and interact with humans just like humans themselves. This requires a lot from the field of Artificial Intelligence. 1.5 Applications :20 1.5 Applications Computer vision applications help to establish tasks which previously required human vision capabilities e.g. recognizing human faces, understanding images and to interpret them, analyzing medical scan and many tasks. Expert systems form probably the largest industrial applications of AI. Software like MYCIN and XCON/R1 has been successfully employed in medical and manufacturing industries respectively. Robotics again forms a branch linked with the applications of AI where people are trying to develop robots which can be rather called as humanoids. Organizations have developed robots that act as pets, visitor guides etc. 1.6 Summary :21 1.6 Summary Intelligence can be understood as a trait of some living species Many

factors and behaviors contribute to intelligence Intelligent machines can be created To create intelligent machines we first need to understand how the real brain functions Artificial intelligence deals with making machines think and act like humans It is difficult to give one precise definition of AI History of AI is marked by many interesting happenings through which the field gradually evolved In the early years people made optimistic claims about AI but soon they realized that its not all that smooth AI is employed in various different fields like gamming, business, law, medicine, engineering, robotics, computer vision and many other fields AI has enormous room for research and posses a diverse future Slide 1: ARTIFICIAL INTELLIGENCE CONTENTS :CONTENTS INTRODUCTION TO A.I. EVOLUTION OF A.I. BRANCHES OF A.I. APPLICATIONS OF A.I. CONCLUSIONS ON A.I.

INTRODUCTION :INTRODUCTION WHAT IS A.I. ? A.I. is a branch of computer science that studies the computational requirements for tasks such as perception, reasoning and learning and develop systems to perform those tasks The field of Artificial intelligence strives to understand and build intelligent entities A.I. Strong A.I. M/C can

think and act like human Weak A.I. Some thinking like features can be added to M/C Slide 4:INTRODUCTION TURING TEST * Intelligence is defined as the ability to achieve human level performance in all cognitive tests, sufficient to fool a human interrogator. * The test was devised in response to the question, Can a computer think ?. * Result was +ve if interrogator can not tell if responses are coming from the M/C or Human. * Proposed by Alan Turing(1950), a British Computer Scientist. Slide 5:INTRODUCTION TURING TEST One person sits at a computer and types the questions. The computer is connected to two other hidden computers At one computer, Human reads and responds to questions. At the other end, computer with no Human aid runs the program to provide responses. Slide 6:INTRODUCTION DEFINITIONS * AI is a branch of computer science dealing with symbolic, nonalgorithmic methods of problem solving * AI is a branch of computer science that deals with ways of knowledge using symbols rather than numbers and with Heuristics, method for processing information. * AI works with pattern matching methods which

attempt to describe objects , events or processes in terms of their qualitative features and logical and computational Relationship. Slide 7:INTRODUCTION What is Intelligence ? To respond to situations very flexibly. To make sense out of ambiguous or contradictory messages. To recognize the relative importance of different elements of situations To find similarities between situations despite difference To draw distinctions between situations despite similarities which may link them. Slide 8:HISTORY 1943 McCulloh and Pitts, Boolean circuit model of brain. 1950 Turings computing machine and intelligence. 1950s Early AI programs including Samuels checker program, Newell and Simons logic theorist, Gelisnters geometry engine 1956 Dartmouth conference. Slide 9:HISTORY 1952-69 Look, Ma, no hands! era. 1958 McCarthy moves to MIT, LISP was born. 1965 Robinsons complete algorithm for logical reasoning. 1966-74 AI discovers computational complex. Neural network research almost disappears. 1969-79 - Early development in knowledge based systems.

Slide 10:HISTORY 1980-88 : Expert system industry booms. 1988-93 : Expert system industry busts. 1985-88 : Neural networks return to popularity. 1995 : Agents Agents Agents. (present) BRANCHES :BRANCHES Logical AI What a program knows about the world in general the facts of the specific situation in which it must act and its goal are all represented by sentences of some mathematical logical language. Pattern Recognition When a program makes observation of some kind, it is often programmed to compare what it sees with already stored patterns. BRANCHES :BRANCHES Representation Facts about the world have to be represented in some way. Usually languages of mathematical logic are used. Common Sense, Knowledge and Reasoning This is an era in which AI is farthest from human level. While there has been considerable progress, e.g. in development systems of non monotonic reasoning and theories of action BRANCHES :BRANCHES Planning Planning programs start with general facts about the world. They generate a strategy for achieving the goal, the

strategy is just a sequence of action. Epistemology This is a study of the kinds of knowledge that are required for solving problems in the world. Ontology It is the study of kinds of things that exist. In AI, things deal with various kinds of object. BRANCHES :BRANCHES Heuristics Heuristics is a way of trying to discover something or an idea embedded in a program. It predicates that compare two nodes in a search tree to see if one is better than other, e.I. constitutes an advance towards the goal, may be more useful. Genetic Engineering It is a technique for getting programs to solve a task by mating random LISP programs and selecting fittest in millions of generations. APPLICATIONS OF A.I. :APPLICATIONS OF A.I. Expert systems. Natural Language Processing (NLP). Speech recognition. Computer vision. Robotics. Automatic Programming. APPLICATIONS :APPLICATIONS EXPERT SYSTEMS An Expert System is a computer program designed to act as an expert in a particular domain (area of expertise). Expert systems currently are designed to assist experts, not to replace them, They have been used in medical diagnosis, chemical analysis, geological explorations

etc. Domain of E.S. Knowledge base Facts Heuristics Phases in Expert System APPLICATIONS :APPLICATIONS Speech Recognition The primary interactive method of communication used by humans is not reading and writing, it is speech. The goal of speech recognition research is to allow computers to understand human speech. So that they can hear our voices and recognize the words we are speaking. It simplifies the process of interactive communication between people and computers, thus it advances the goal of NLP. APPLICATIONS :APPLICATIONS Natural Language Processing The goal of NLP is to enable people and computers to communicate in a natural (humanly) language(such as, English) rather than in a computer language. The field of NLP is divided in 2 categories Natural Language understanding. Natural Language generation. APPLICATIONS :APPLICATIONS Computer Vision People generally use vision as their primary means of sensing their environment, we generally see more than we hear, feel or smell or taste. The goal of computer vision research is to give computers this same powerful facility for

understanding their surrounding. Here AI helps computer to understand what they see through attached cameras. APPLICATIONS :APPLICATIONS Robotics A Robot is a electro-mechanical device that can by programmed to perform manual tasks or a reprogrammable multi functional manipulator designed to move materials, parts, tools, or specialized devices through variable programmed motions for performance of variety of tasks. An intelligent robot includes some kind of sensory apparatus that allows it to respond to change in its environment. Slide 21:APPLICATIONS Robotics APPLICATIONS :APPLICATIONS Automatic Programming Programming is a process of telling a computer exactly what you want it to do.Writing a program is a tedious job. It must be designed, written, tested, debugged and evaluated. The goal of automatic planning is to create special programs that act intelligent tools to assist programmers and expedite each phase of programming process. Ultimate aim is computer itself should develop a program in accordance with specifications of programmer.

FUTURE :FUTURE The day is not far when you will just sit back in your cozy little beds and just command your personal Robot's to entirely do your ruts . He will be a perfect companion for you. Just enjoy the Technology. FUTURE :FUTURE But wait, dont be happy. It may end in other way too. Some day there will be a knock to your door. As you open it, you see a large number of Robots marching into your house destroying everything you own and looting you. This is because ever since there is an advantage in the Technology, it attracts anti-social elements. This is true for Robots too. Because now they will have full power to think as human, even as of anti-social elements. So think trice before giving them power of Cognition. CONCLUSION :CONCLUSION In its short existence, AI has increased understanding of the nature of intelligence and provided an impressive array of application in a wide range of areas. It has sharpened understanding of human reasoning, and of the nature of intelligence in general. At the same time, it has revealed the complexity of modeling human reasoning providing new areas and rich

challenges for the future. Machine Translation

(a subtopic of Natural Language)

"A renewed international effort is gearing up to design computers and software that smash language barriers and create a borderless global marketplace." - Steve Silberman

"What is Machine Translation? Machine translation (MT) is the application of computers to the task of translating texts from one natural language to another. One of the very earliest pursuits in computer science, MT has proved to be an elusive goal, but today a number of systems are available which produce output which, if not perfect, is of sufficient quality to be useful in a number of specific domains." A definition from the European Association for Machine Translation (EAMT), "an organization that serves the growing community of people interested in MT and translation tools, including users, developers, and researchers of this increasingly viable technology." Me Translate Pretty One Day - Spanish to English? French to Russian? Computers haven't been up to the task. But a New York firm with an ingenious algorithm and a really big dictionary is finally cracking the code. By Evan Ratliff. Wired (December 2006; Issue 14.12). "Jaime Carbonell, chief science officer of Meaningful Machines, hunches over his laptop in the company's midtown Manhattan offices, waiting for it to decode a message from the perpetrators of a grisly terrorist attack. Running software that took four years and millions of dollars to develop, Carbonell's machine -- or rather, the server farm it's connected to a few miles away -- is attempting a task that has bedeviled computer scientists for half a century. The message isn't encrypted or scrambled or hidden among thousands of documents. It's simply written in Spanish:.... Language translation is a tricky problem, not only for a piece of software but also for the human mind."

After you read the article, be sure to visit Meaningful Machines, The Language Technologies Institute (LTI) at Carnegie Mellon University, and The Center for Computational Learning Systems (CCLS) at Columbia University.

Mark my words. The Economist (February 16, 2007). "For those who put their faith in technology, therefore, it was encouraging to hear Shinzo Abe, Japans prime minister, demonstrate his linguistic skills a few weeks ago with a palm-sized gizmo that provided instantaneous translations of spoken Japanese into near-flawless English and Chinese. ... [T]he fact that a pocket-sized device could interpret tourist-type phrases accurately and on the fly, from one language to several others, says much about the improvements that have been made lately in machine translation. This device, developed by the Advanced Telecommunications Research Institute International near Kyoto.... Machine translation has been an elusive goal since the earliest days of computer science. ... The main drivers for this more pragmatic approach to machine translation have been the enlargement of the European Union and the spread of the internet. Both have generated a pressing need for cheap and cheerful translations between numerous languages. In turn, this has spawned a wealth of new translation approaches." Translation Tools - New Approaches to an Old Discipline. Automated translation tools have been around for a long time, and new techniques are boosting their performance. But use them with caution. By Gary Anthes. Computerworld (August 13, 2007). "Language translation software isnt likely to allow you to lay off your bilingual staffers -- at least not right away. But applied with discrimination and lots of preparation, translation tools can be fantastic productivity aids. And researchers say new approaches to this old discipline are greatly improving the performance of the tools. Ford Motor Co. began using 'machine translation' software in 1998 and has so far translated 5 million automobile assembly instructions into Spanish, German, Portuguese and Mexican Spanish. Assembly manuals are updated in English every day, and their translations -some 5,000 pages a day -- are beamed overnight to plants around the world. 'It wouldnt be feasible to do this all manually,' says Nestor Rychtyckyj, a technical specialist in artificial intelligence (AI) at Ford. ... Systrans tool uses a tried-and-true translation technique called rules-based translation. ... Statistical machine translation is a newer technique thats not yet in widespread use. It uses collections of documents and their translations to 'train' software. Over time, these data-driven systems 'learn' what makes a good translation and what doesnt and then use probability and statistics to decide which of several possible translations of a given word or phrase is most likely correct based on context. ... 'The new direction in the research community is to see how you can combine these purely statistical techniques with some linguistic knowledge,' says Steve Richardson, a senior researcher at Microsoft. 'Its modeling the rules with the statistical methods.' ... Automated translation in the corporate world succeeds to the extent that users are willing to carefully customize systems to their unique needs and vocabularies, he says. And the technology is most appropriate when translations dont have to be perfect. 'We have serviced thousands and thousands of customers with articles we have machine-translated,' Richardson says. 'Its not perfect, but its good enough. They get an answer without calling in. Whats that worth to the company' ... [H]ybrid systems, which combine translation memories and machine translation based on rules or statistics or both, are the wave of the future, researchers say, and they are becoming more sophisticated and complex. ... In essence, SRIs approach is to do machine translations with the best available rules-based and statistical-based systems, and then have another system that 'adjudicates' among them in real time to find the best translation."

Also see: Machine Translation for Manufacturing - A Case Study at Ford Motor Company. By Nestor Rychtyckyj. AI Magazine 28(3): Fall 2007, 31.Abstract: "Machine translation (MT) was one of the first applications of artificial intelligence technology that was deployed to solve real-world problems. Since the early 1960s, researchers have been building and utilizing computer systems that can translate from one language to another without requiring extensive human intervention. In the late 1990s, Ford Vehicle Operations began working with Systran Software Inc. to adapt and customize its machine-translation technology in order to translate Fords vehicle assembly build instructions from English to German, Spanish, Dutch, and Portuguese. The use of machine translation was made necessary by the vast amount of dynamic information that needed to be translated in a timely fashion. The assembly build instructions at Ford contain text written in a controlled language as well as unstructured remarks and comments. The MT system has already translated more than 7 million instructions into these languages and is an integral part of the overall manufacturing process-planning system used to support Fords assembly plants in Europe, Mexico and South America. In this paper, we focus on how AI techniques, such as knowledge representation and natural language processing can improve the accuracy of machine translation in a dynamic environment such as auto manufacturing."

Watch Ron Brachman demonstrate the Phraselator on The Charlie Rose Show episode: A panel discussion about Artificial Intelligence (December 21, 2004), with Rodney Brooks (Director, MIT Artificial Intelligence Laboratory & Fujitsu Professor of Computer Science & Engineering, MIT), Eric Horvitz (Senior Researcher and Group Manager, Adaptive Systems & Interaction Group, Microsoft Research), and Ron Brachman (Director, Information Processing Technology Office, Defense Advanced Research Project Agency, and President, American Association for Artificial Intelligence). The segment begins at 20:34. Top minds taxed by translation challenge - Creating a real-time translating machine is harder than it seems. By Brian Bergstein. The Associated Press /available from MSNBC.com (November 5, 2006). "The past few years have shown that U.S. government intelligence goes only so far. One of the biggest challenges is recognizing vital information in foreign languages -- and acting quickly on it. That's why the military would love software that can listen to TV broadcasts or phone conversations and read Web sites in Arabic and Chinese, translate them into English and summarize the key elements for humans. ... Last year DARPA launched a project that aims to create that real-time translation software. Its called GALE, for Global Autonomous Language Exploitation." Tech Solutions to Iraqi-U.S. Language Barrier. Xeni Jardin's Xeni Tech report for NPR's Day to Day (November 13, 2006: audio available). "Part of the daily struggle for soldiers and Marines in Iraq is communicating with civilians and suspected insurgents. Few military personnel have enough fluency with Iraqi Arabic to be easily understood, and field translators are in short supply. But technology may help close that communications gap. A hand-held voice translator device developed by Integrated Wave Technologies,

already in use in other parts of the world, converts simple English commands into Iraqi Arabic or 15 other languages." Military getting high-tech help from SRI lab - New system can recognize words, understand simple foreign phrases. By Tom Abate. San Francisco Chronicle & SFGate.com (May 29, 2006). "During a recent product demonstration at SRI headquarters in Menlo Park, computer scientist Harry Bratt spoke into the microphone of his lab's new translation computer: 'Did you hear the explosion this morning?' Several seconds later, software written by SRI International scientists piped the question through the computer's speaker -- this time in the Iraqi dialect of Arabic. Saad Alabbodi, an Iraqi immigrant posing as a civilian being questioned by a U.S. soldier, answered in his native tongue. There was another pause as the computer translated Alabbodi's reply into English in a mock interrogation that provided another example of how technology is slowly mimicking complex human capabilities such as speech. [Go to the related podcast to hear the actual conversation.] ... 'One of the crying needs in Iraq is overcoming the language barrier,' said Kristin Precoda, director the SRI lab that developed the two-way translation system called IraqComm."

Also see: August 23, 2006: How to Talk Like an Iraqi - Laptop software that can translate English-Arabic conversations on the fly is being tested in Iraq. By Kate Greene. Technology Review (August 23, 2006). "Overcoming language barriers can be a matter of life or death in Iraq. Soldiers, medical personnel, and Iraqi citizens struggle to convey crucial information on a daily basis. While human translators are used in many situations, there simply aren't enough who are willing to assist in every important conversation. Last month, Palo Alto-based SRI International announced that it had deployed 32 Windows XP laptops loaded with advanced translation software for military evaluation in Iraq. The software, called IraqComm, facilitates an English-Arabic conversation by recording a person's spoken words, translating them, and playing the translation in a matter of seconds. ... After DynaSpeak converts the spoken words into text, software performs the translation. The software consists of two components, developed with the assistance of the Information Sciences Institute (ISI) at the University of Southern California (USC) in Los Angeles. The first module uses rule-based algorithms, explains [Kristin] Precoda, written to recognize specific rules of grammar and usage. ... [F]or more complicated sentences, the translation software turns to a type of algorithm that performs a kind of statistical analysis on the language. ... The goal of IraqComm is not to put human translators out of business, emphasizes SRI's Precoda. ... Unlike human translators, however, IraqComm can be deployed anywhere and everywhere. Ultimately, then, says Precoda, it can give the military more translation options and help to mitigate the wartime hazard for Iraqi translators."

Google's Peter Norvig on managing the data deluge. Video of talk delivered on September 25, 2006 at UC Berkeley as part of the CITRIS Distinguished Speaker Series. "Researchers in computational linguistics and information retrieval now have a million times more data than was available 30 years ago. In this talk, Peter Norvig explores what

this data can do for problems in language understanding, [statistical machine] translation, information extraction, and inference, and extrapolates to what more data may bring in the future." Machine Translation - Inching toward Human Quality. "In the News" article by Jan Krikke. IEEE Intelligent Systems (March/April 2006; 21(2): 4-6). "After 50 years of research and tinkering,machine translation might be ready to compete with human translators. Several companies have announced breakthroughs or substantial progress in MT research in recent months. ... MT requires complex cognitive operations to perform a seemingly mundane task: decoding a source text and recoding into the target language. The three common methods are rule-based MT(RBMT), statistical MT(SMT), and example-based MT (EBMT)."

Also see this related news article: Google dominates in machine translation tests.By Michael Kanellos.CNET News.com(August 22, 2005).

An overview of machine translation, by John Hutchins (University of East Anglia, United Kingdom: updated January 2005), is available from the British Computer Society'sNatural Language Translation Specialist Group.

Also see John Hutchins' Machine Translation website for additional resources such as: o his collection of "[a]rticles, books and papers about machine translation and computer-based translation tools, the historical development and current use of computers for the translation of natural languages."

Machine Translation: An Introductory Guide. By Doug Arnold, Lorna Balkan, Siety Meijer, R.Lee Humphreys and Louisa Sadler (1994). "The topic of the book is the art or science of Automatic Translation, or Machine Translation (MT) as it is generally known --- the attempt to automate all, or part of the process of translating from one human language to another. The aim of the book is to introduce this topic to the general reader --- anyone interested in human language, translation, or computers." "The international center for Advanced Communication Technologies, interACT, is a joint center between the Universitt (TH), Karlsruhe, Germany and Carnegie Mellon University, Pittsburgh, USA."

See these related news articles.

Scaling the Language Barrier. By Sebastian Rupley. PC Magazine (July 13, 2004). "In the annals of computer comedy, one of the most famous anecdotes is about asking a speech recognition engine, 'Recognize speech?' The translation comes back: 'Wreck a nice beach.' Getting machines to understand both spoken and written language has been an elusive goal for the tech industry for many years. Now, thanks to a wave of government funding and technical breakthroughs, machine translation (and understanding) of written language is getting unfunnier by the minute. ... The one clue

Meaningful Machines has given about its software is that it will use new methods of statistically ranking the likelihood of what entire phrases mean, rather than just translating one word at a time. That allows it to discern whether the word baseball in a given phrase refers to a ball or a game. ... Carnegie Mellon University, the University of Southern California, and Microsoft Research operate some of the largest programs for developing machine translation software. Microsoft is primarily focused on extracting meaning from documents in English." E-translators - the more you say, the better, By Gregory M. Lamb. The Christian Science Monitor (April 22, 2004). "Universal translation is one of 10 emerging technologies that will affect our lives and work 'in revolutionary ways' within a decade, Technology Review says." Speech-to-Speech Translation. IBM Research. "The goal of the Speech-to-Speech Translation (S2S) research is to enable real-time, interpersonal communication via natural spoken language for people who do not share a common language. The Multilingual Automatic Speech-to-Speech Translator (MASTOR) system is the first S2S system that allows for bidirectional (English-Mandarin) free-form speech input and output.The research leading to MASTOR was initiated in 2001 as an IBM adventurous research project and was also selected to be funded by the Defense Advanced Research Projects Agency (DARPA) CAST program (formerly called 'Babylon' program). ... Construction of robust systems for speech-to-speech translation to facilitate cross-lingual oral communication has been the dream of speech and natural language researchers for decades. It is technically extremely difficult because of the need to integrate a set of complex technologies Automatic Speech Recognition (ASR), Natural Language Understanding (NLU), Machine Translation (MT), Natural Language Generation (NLG), and Text-to-Speech Synthesis (TTS)...." Links to publications and additional information appear at the bottom of their page. Robo-talk helps pocket translator. By Jo Twist. BBC News (March 4, 2004). "Visitors landing at Tokyo's Narita Airport will be able to hire a device which can translate the local lingo. The speech-to-speech technology was developed by NEC, tested in Papero robots and then put in PDAs. ... As well as being able to understand and imitate human behaviour, Papero (Partner-Type Personal Robot), is the first robot to translate verbally between two languages in colloquial tongue. It can cope, in other words, with slang and local chatter, and has a vocabulary of 50,000 Japanese and 25,000 English travel and tourism related words." Computer aid ensures speedy, high-quality translations. IST Results (January 12, 2005). "Increasing translators' productivity is the goal of TransType2, an innovative computeraided system that allows rapid and efficient high quality translations. Due to end in February, the 36-month IST programme project has drawn on two of the most commonly used translation technologies developed to date: Computer-Assisted Translation (CAT), in which human translators work in unison with a computer; and Machine Translation (MT), in which the computer handles the entire process. While both techniques have

advantages and drawbacks, TransType2 has 'used the best of both worlds' says project manager Jos Esteban at Atos Origin in Spain." Software learns to translate by reading up. By Will Knight. NewScientist.com news service (February 22, 2005). "Translation software that develops an understanding of languages by scanning through thousands of previously translated documents has been released by US researchers. Most existing translation software uses hand-coded rules for transposing words and phrases. But the new software, developed by Kevin Knight and Daniel Marcu at the Information Sciences Institute, part of the University of Southern California, US, takes a statistical approach, building probabilistic rules about words, phrases and syntactic structures. The pair founded a company called Language Weaver in Los Angeles, US, to sell the software as an automated translation tool."

Visit Language Weaver's web site.

The Translation Challenge. By Chip Walter. Technology Review (June 2003). "Researchers are making progress today using three basic approaches drawn from natural-language processing. Knowledge-based machine translation, for example, relies on human programmers to write lists of rules that describe all possible relationships between verbs, nouns, prepositions, and so on for each language. ... A second approach, example-based systems, relies chiefly on raw computing power. ... Statistical techniques also depend on computing power to compare reams of previously translated text. However, this strategy selects the most likely translation using sophisticated mathematical models that the software continually upgrades based on how often its interpretations prove accurate." Another Step Closer to Artificial Intelligence. DW-WORLD.DE. (December 1, 2001) "This year's prestigious German Future Prize has been awarded to the inventor of an electronic translating device which brings humanity one step closer to the concept of Artificial Intelligence. ... [Professor Wolfgang] developed the 'Verbmobile'. This is essentially a computer that translates between German, English and Japanese."

Find out more about the Verbmobil at the German Research Center for Artificial Intelligence (DFKI GmbH).

The World Wide Translator. Will Web-wide "translation memory" finally make machine translation pay off? "Hour is the moment for all the good men to come to the subsidy of them country." By Alan Leo. MIT Technology Review (September 21, 2001). "'This whole area of language is extremely complex,' says IDC analyst Steve McClure. 'It's probably the most complicated problem in computer science that I'm aware of.' Computer-assisted translation typically involves two steps. First, a rules engine parses the original sentence, attempting to identify the relationships between the words. The engine then translates each word within the context that it believes to be correct-- often with mixed results." You can translate text of your choice by using free translators such as these from:

AltaVista Applied Language SDL International GOOGLE InterTran SYSTRAN IBM Research Demonstrates Innovative 'Speech to Sign Language' Translation System. IBM press release via Market Wire. (September 13, 2007). "IBM (NYSE: IBM) has developed an ingenious system called SiSi (Say It Sign It) that automatically converts the spoken word into British Sign Language (BSL) which is then signed by an animated digital character or avatar. SiSi brings together a number of computer technologies. A speech recognition module converts the spoken word into text, which SiSi then interprets into gestures, that are used to animate an avatar which signs in BSL. ... This project is an example of IBM's collaboration with non-commercial organisations on worthy social and business projects. The signing avatars and the award-winning technology for animating sign language from a special gesture notation were developed by the University of East Anglia and the database of signs was developed by RNID (Royal National Institute for Deaf People). ... SiSi has been developed in the UK by a research team at IBM Hursley, as part of IBM's premier global student intern programme, Extreme Blue. In the European part of the programme, 80 of the most talented students from across Europe were selected to work on 20 projects and given whatever equipment, support and assistance they required. Working for an intense 12 week period alongside IBM technical and industry leaders, they focused on innovative technology projects, such as SiSi, all of which had real business value. ... For a video demonstration of the SiSi technology, visit the following url: http://youtube.com/watch?v=RarMKnjqzZU" The DePaul University American Sign Language (ASL) Synthesizer. "Combining computer technology and linguistics research to bridge the communication gap between the deaf and hearing worlds, our team of deaf and hearing researchers is working towards the realization of a digital English-to-ASL translator." Visit their site and meet "Paula," a virtual interpreter.

Computer Program Translates Spoken English Into Sign Language. AScribe Newswire / available from National Geographic (August 12, 2002). "Paula is a computer-generated synthetic interpreter developed by a team of faculty and students in the School of Computer Science, Telecommunications and Information Systems at DePaul University in Chicago. The system works like this: A hearing person speaks through a headset, which is connected to the computer. The computer processes the command, and the animated figure of Paula translates the message into ASL through hand gestures and facial expressions on the computer screen." Animated interpreter translates spoken English into sign language for travelers. By Liz Austin. The Associated Press. "Navigating airport security is stressful for anyone these days. But it's even harder if you're deaf. ... Computer scientists from DePaul University believe they have a solution: a 3-D animated interpreter that

can translate spoken English into American Sign Language. Using speech recognition and animation software, the team has created 'Paula'" an animated figure that translates simple sentences into the hand and body positions, configurations and facial expressions that make up ASL." I See What You Are Saying. By Dr. Judith Markowitz. Speech Technology Magazine (September/October 2003). "Theres no doubt that speech recognition is an assistive technology. ... The goal of the DePaul researchers is to capture spoken instructions and convert them into the fourth most widely-used language in the United States -- American Sign Language (ASL). 'This involves transforming verbal communication into an animated visual format,' says graduate student Sunny Srinirasan. 'Its really a machine-translation project where the translation is from sounds to hand movements and positions.'"

Speech, Language & Virtual Human Research at the School of Computing Sciences, University of East Anglia. Here's where you'll find Guido, a "virtual signer" (see this May 5, 2005 press release) and TESSA & VANESSA. GRASP - Recognising Auslan signs using Instrumented Gloves. Waleed Kadous' Honour Thesis (1995), School of Computer Science and Engineering at the University of New South Wales. "You may also be interested in my Machine Gesture and Sign Language Recognition page, but I have to warn you that it's a little out of date." Digital characters 'talk' to the deaf. By Jon Wurtzel. BBC (March 2, 2002). "Using digital avatars as signing translators could significantly expand the ways deaf and hard of hearing people communicate with the hearing world. The avatars are computer animations designed to look and move like real people. A computer program takes spoken English and converts it in real-time to text. The digital avatars then take this English text and sign its meaning on a display screen, in effect becoming a translator between spoken English and British sign language. ... Businesses should pursue this technology, and not just because it is the right thing to do. The deaf and hard of hearing account for 8.6 million of the 59 million people in the UK. Combine that with the millions throughout the world who would also benefit, and a huge market opportunity emerges for the right products."

Find out more about this field on our Assistive Technologies page.

Talking to Strangers. By Steve Silberman. Wired (May 2000; 8.05). "A renewed international effort is gearing up to design computers and software that smash language barriers and create a borderless global marketplace."

Machine Translation's Past and Future. A timeline from Wired covering the span from 1629 through the year 2264! Compiled by Kristin Demos and Mark Frauenfelder. Universal Translators - A look at the hubs for machine translation R&D worldwide. Compiled by Carl Zimmer. And also see the rest of the translation related articles in this issue of Wired.

Lost in Translation. By Stephen Budiansky. The Atlantic Monthly (December 1998 / Volume 282, No. 6; pages 80 - 84). "In one famous episode in the British comedy series Monty Python a foreign-looking tourist clad in an outmoded leather trenchcoat appears at the entrance to a London shop. He marches up to the man behind the counter, solemnly consults a phrase book, and in a thick Middle European accent declares, 'My hovercraft ... is full of eels!' ... This episode is brought to mind by some recently available computer programs that claim to provide automatic translation between English and a number of other languages. Translation software that runs on mainframe computers has been used by government agencies for several decades, but with the advent of the Pentium chip, which packs the power of a mainframe into a desktop, such software can now easily be run on a personal computer."

Also see this article from the August 1959 issue of The Atlantic Monthly: The Translating Machine, by David O. Woodbury. "Professor William N. Locke, head of MIT's modern languages department and a prime mover in machine translation, is not going to be satisfied even with this kind of short cut. He would like to have a machine that will translate material that is merely spoken to it. This is not so fantastic as it sounds." (Volume 204, No. 2; pages 60 - 64.)

"The Center for Machine Translation (CMT) is a research branch of the School of Computer Science [at Carnegie Mellon University] devoted to basic and applied research in all aspects of natural language processing, with a primary focus on machine translation, speech processing, and information retrieval. Containing a unique mix of academic and industrial researchers specializing in various aspects of computer science, artificial intelligence, computational linguistics and theoretical linguistics...."

Be sure to check out their current research such as DIPLOMAT (Distributed Intelligent Processing of Language for Operational Machine Aided Translation) and the Lockheed-Martin-led Tongues project.

Association for Machine Translation in the Americas. "AMTA is an association dedicated to anyone interested in the translation of languages using computers in some way. This includes people with translation needs, commercial system developers, researchers, sponsors, and people studying, evaluating, and understanding the science of machine translation (MT) and educating the public on important scientific techniques and principles involved. ... AMTA has members in Canada, Latin America, and the United States. It is the regional component of a worldwide network headed by the International Association for Machine Translation (IAMT)." Automating Knowledge Acquisition for Machine Translation. By Kevin Knight. AI Magazine, 18(4): Winter 1997, 81-96. "Machine translation of human languages (for example, Japanese, English, Spanish) was one of the earliest goals of computer science research, and it remains an elusive one. Like many AI tasks, translation requires an immense amount of knowledge about language and the world. Recent approaches to machine translation frequently make use of text-based learning algorithms to fully or partially automate the acquisition of knowledge. This article illustrates these approaches."

Some DARPA projects:

One-way Phrase Translation System (PTS) Phraselator also see the National Institute of Standards and Technology's Machine Translation Benchmark Test and the 2005 results.

Semantic Networks. By John Sowa. "A semantic network or net is a graphic notation for representing knowledge in patterns of interconnected nodes and arcs. Computer implementations of semantic networks were first developed for artificial intelligence and machine translation, but earlier versions have long been used in philosophy, psychology, and linguistics." Language Translation (TRL) at IBM. "This project deals with natural language analysis and translation by computer. Technologies used for machine translation, such as syntactic parsing and word sense disambiguation, are commonly used for other applications of natural language processing."

Also see this December 2004 article from AI in the news.

Abstract Real-time strategy is one of the most important game genre from the beginning of the computer games history and one of the biggest inner market in computer games market, in spite of that fact there are only a few strategy games have successful AIs. This paper will try to improve real-time strategy games AI by improving long term decisions such as; resource management, determining correct buildings to build, achieving correct upgrades/technologies with neural networks as well as to short term decisions such as; creating correct troops against opponents troops, determination of attacking or fleeing, attacking to correct enemy troops. Also this paper will try to give examples from strategy games such as Command and Conquer: Tiberium Wars, Age of Empires. Key Words: Artificial intelligence in real-time strategy games, fuzzy logic, neural networks, short term decision making in strategy games, long term decision making in strategy games.

1. Definition of Fuzzy Logic

The best definition of fuzzy logic is given by its inventor Lotfi Zadeh; Fuzzy logic means of representing problems to computers in a way akin to the way human solve them and the essence of fuzzy logic is that everything is a matter of degree. The meaning of solving problems with computers akin to the way human solve can easily be explained with a simple example from a basketball game; if a player wants to guard another player firstly he should consider how tall he is and how his playing skills are. Simply if the player that he wants to guard is tall and plays very slow relative to him then

he will use his instinct to determine to consider if he should guard that player as there is an uncertainty for him. In this example the important point is the properties are relative to the player and there is a degree for the height and playing skill for the rival player. Fuzzy logic provides a deterministic way for this uncertain situation. There are some steps to process the fuzzy logic (Figure-1). These steps are; firstly fuzzification where crisp inputs get converted to fuzzy inputs secondly these inputs get processed with fuzzy rules to create fuzzy output and lastly defuzzification which results with degree of result as in fuzzy logic there can be more than one result with different degrees.

Figure 1 Fuzzy Process Steps (David M. Bourg P.192) To exemplify the fuzzy procee steps, the previous basketball game situation could be used. As mentioned in the example the rival player is tall with 1.87 meters which is quite tall relative to our player and can dripple with 3 m/s which is slow relative to our player. Addition to these data some rules are needed to consider which are called fuzzy rules such as;

if player is short but not fast then guard, if player is fast but not short then dont guard If player is tall then dont guard If player is average tall and average fast guard

Figure 2 how tall

Figure 3- how fast

According to the rules and the input data an output will be created by fuzzy system such as; the degree for guard is 0.7, degree for sometimes guard is 0.4 and never guard is 0.2.

Figure 4-output fuzzy sets On the last step, defuzzication, is using for creating a crisp output which is a number which may determine the energy that we should use to guard the player during game. The centre of mass is a common method to create the output. On this phase the weights to calculate the mean point is totally depends on the implementation. On this application it is considered to give high weight to guard or not guard but low weight given to sometimes guard. (David M. Bourg, 2004)

Figure 5- fuzzy output (David M. Bourg P.204) Output = [0.7 * (-10) + 0.4 * 1 + 0.2 * 10] / (0.7 + 0.4 + 0.2) -3.5

As a result fuzzy logic is using under uncertainty to make a decision and to find out the degree of decision. The problem of fuzzy logic is as the number of inputs increase the number of rules increase exponential.

2. Definition of Artificial Neural Networks

Although there is no agreed definition the most common definition is it involves a network of simple processing elements (neurons), which can exhibit complex global behaviour, determined by the connections between the processing elements and element parameters (Wikipedia, Artificial neural network). The structure of ANN (Artificial Neural Networks) is same with humans neural networks structure as in human neural system there are receptors to collect the data named dendrites, a processing unit named cell body and an output unit named axon. Similar to this structure in ANN there is an input layer, a processing unit which sums the inputs after multiplying them with weights and an output layer which gives a result for a neuron (Figure 6).

Figure 6- structure of a simple neuron (Mat Buckland, 2002, p.241) As seen in the figure the output will depend on the inputs and the weights as well. This is the main point of the ANN as if we can find the correct weights for the inputs than we can create a correct result for ever situation. On reverse order if we know have the inputs and if we know the results for every input pair than we can calculate the weights therefore after finding weights if we give input values to our neural network it can calculate the correct output for certain input pairs. This method which is called back propagation is a supervised learning. The problems of that method are; training sets for feeding the ANN may not have all the possibilities or these sets may contain novel data (Dr Emma Hart, 2005). Although the logic sounds pretty easy for ANNs with supervised learning, there is a mathematical background which makes this logic work for computers. On this part of this

paper no mathematical background will be explained since it is not the main goal of this paper. (To get more information about ANNs please check further reading)

Figure 7- structure of a neural network with one input layer, one hidden layer and one output layer (Mat Buckland, 2002, p.242) As seen in the figure above there is a hidden layer which is necessary to make complex calculations. A neural network without hidden layer can make logical calculations such as AND and OR but cannot calculate XOR operation. This means that for complex calculations the hidden layer is obviously necessary. The number of neurons in the hidden layer is up to implementation. Increasing number of hidden layers increases the precision and complexity of the calculations which results with accurate calculations with using more CPU time and more memory that is the trade off. To find the best number of hidden layers the only way is experimenting different values, however, there are different estimations for that problem such as square root of number of input layers multiply by number of output layer. In brief, ANNs are using for complicated or imprecise data and also for recognising the patterns (Christos Stergiou, NEURAL NETWORKS). Recognition of patterns requires very complicated methods and data structures with classic methods; however ANNs are very simple structures which make the implementation easier as ANNs are selforganising structures as well. The cons of ANNs with back propagation supervised learning are; high consumption of resources, choosing correct propagation sets, choosing correct number of hidden layers and hard debugging.

3. Real Time Strategy Games (RTS Games)

A RTS game is a strategic game which runs in real time distinguish it from turn based strategy games. Although the high number of RTS games there are only a few scenarios

are used for these games. The most popular scenario starts with a couple of productive units such as villagers, and a few resources. The player should use the villagers to collect resources and create new buildings or units who can be soldiers or villagers. The buildings usually enable new unit tapes. To give an example the player can create knights by using stable and to build a stable a barracks should have been built. On the other hand to upgrade the unit strength usually players should achieve new technologies which are usually much costly than unit production. As seen in this scenario usually in RTS games there is a hierarchical order which the player should follow to defeat the enemy. Although there is a static hierarchical order for creation of units or achievement of technologies, always complex algorithms running for RTS games AI since the number of probabilities and parameters are very high for making decisions. Moreover the only problem in RTS games is not decision making but also path finding or this kind of AI algorithms but in this paper only decision making will be discussed. In the history of RTS games, game AIs usually statically programmed like finite state machines for decision making. To give an example AOE-2 (Age of Empires II) has a rule based AI with priority queues which means nearly static development for NPC (non player character). If the player can find a way to defeat the NPC than the player will never lose again as the NPC cannot evolve itself and cannot find a way to overcome the bottlenecks of its management strategy. Besides these long term decision failures in AOE-2 consideration mechanism for choosing the correct the enemy to attack is not working at all as the troops always choose and attack an enemy until they die. This makes the game AI dummy since if the human player creates a trap with a wall such as builds a wall around an archer, all the knights try to attack this archer but they are not able to attack because of the wall but they lose lots of energy or time. Even if the AI programmer can find out this bug and tries to prevent this situation, he has to write lots of scripts as there is no rule to generalise in this situation. That makes the AI very complicated. Thankfully in new generation games such as Command Conqueror Tiberium Wars, the troops behave reasonable as they can choose the correct troop to attack according to its health. To give an example all the troops choose the enemy with lowest health in their range but this approach still involves some problems. Moreover this game has obviously problem while making long term decisions because NPC obviously cheats by having lots of recourses and by producing them very fast. These approaches make strategy games very boring for game players as if the game player can defeat NPC for once then computer nearly has no chance to win again. Thats because of their static structure and behaviours. To find alternative solutions for these problems in this paper the decisions will be divided into two parts according to their importance. If the decision is unit wise such as choosing the correct troop in the range to attack will be called as short term decision. On the other hand the decisions, like choosing correct technologies to achieve, which are not individual decision for a troop but about a certain group of all troops in the game or the decisions which will affect the destiny of the game for long term will be called long term decisions.

Not only the importance but also the complexity of the decisions is another reason for this differentiation. The short term decisions such as considering the correct troop to build is a less complex decision compare to resource management and it is only uncertain which means can be found out by analysing some other parameters. However the resource management cannot be done by analysing some parameters because of the huge amount of the parameters and complex relations between these parameters.

a. Short Term Decisions in Real Time Strategy Games

As mentioned before, short term decision means instantaneous decisions made by individual troops or the controlling mechanism such as; decision of attacking or fleeing or creating the correct troops according to immediate data. Although these kind of short term decisions are unpredictable, they can be made by deterministic calculations such as Fuzzy Logic which provides a high resolution for output with crisp input data. In the next parts of this paper, these short term decisions will be discussed in terms of their input data, output data and the way to make these decisions with the explanations. The sections below based on a hypothetical RTS game scenario. In this hypothetical RTS game the units have the properties showed on the list below with explanations. Health The health of the troop, in fuzzy set it will be normalized range between [0,100], 100 represents the healthiest and 0 is death. Unlike some of the RTS games, in this example there is only one type of armour for the troop which reduces the attack power of enemy against the troop. Attack power of troop against the enemy. Attack speed is the variable defines how many time can the troop attack to the enemy in a constant time interval Differs from attack speed, this is the parameter to define how fast the troop move or escape, it is constant for every type of the troops.

Armour

Attack Power Attack Speed Movement Speed

And the parameters are found by some calculations using the variable above. The main reason for doing that is having more realistic information. To give an example, lets assume there is two kinds of troops first one with attack power of 50 and attack speed of 1, the other troop has the attack power of 15 with the speed of 4. This means that while the first troop causes 501 = 50 units of damage in T seconds but the second troop causes 154 = 60 units of damage which means the second troop is stronger than second one.

Relative Attack Power

OAS = Own Attack Speed EAS = Enemys Attack Speed = Sum of the powers of the troops attacking to the target troop = The target troops armour = Sum of the powers of the enemy troops attacking to the troop = Enemy troops armour in the aim of the troop = The troops Armour. This variable normalized by multiplying with 50. The result of 50 means equality.

Relative Speed

= Own Movement Speed = Enemys Movement Speed = The mean of the speeds of the attacking troops to the target troop.

= The mean of the speeds of the enemy troops attacking to the troop. This variable normalized by multiplying with 50. The result of 50 means equality. The usage of symbol adds the group behaviour for the decision making. To give an example, if the Team A has only one troop with good condition in terms of its health, on the other side Team B has five troops and all of them heavily injured but has the opportunity to destroy the enemy troop. On this condition if the consideration algorithm

runs on only the troops one by one than all the Team B troops should escape from the clash but actually they shouldnt since they can destroy the enemy. Another example for better understanding can be given from the figure below. The troop with number 7 from the Square Team is attacking to the troop with number 2 from the Circle Team and the number 2 is being attacked by number 8 as well. On the other hand number 7 is being attacked by number 3. On this condition RAP (Relative Attack Power) of number 7 will be calculated by sum of powers of number 7 and number 8 divide by the attacking power of number 3. So the equation for RAP is;

Equation 1 RAP Equation for Troop 7

Figure 8 A clash example between two forces

i.

Attack or Flee

In a RTS game one of the most usual decisions to be made is the individual decision of a troop to continue attacking or start fleeing. In most of the RTS games like; warcraft, dune 2000, command conqueror as well as age of empires these kinds of decisions made by FSM (finite state machines). The main reason for these games to use finite state machines can be predict as reducing the CPU time for game AI as FSM is a static structure which needs minimum amount of resources but the problem of this structure is the number of states and unrealistic behaviour. Apart from FSMs another approach can be the Fuzzy logic which provides realistic behaviour but consumes more CPU time but this is a trade off and acceptable due to the increasing CPU/GPU power.

The first stage to setup the fuzzy logic is determination of Fuzzy Input data Sets (FIS) and membership functions. However its better to define the Fuzzy Output Set (FOS) and its membership functions as we have only two FOSs; first one is Attack, second one is Flee (figure-9).

Figure 9 Fuzzy output sets and member functions The FISs are Own Health, Enemys Health, Relative Attack Power (RAP), Relative Movement Speed (RMS). With the help of these variables the troop will show the group behaviour and make realistic decisions. The other step is determination of membership function. On this paper only linear membership functions such as triangle and trapezoid used for easy understanding as well as easier calculation, however it is better to use logarithmic curves for RAP and RMS since they are the results of division of two forces and two speeds. For both of these data sets 50 represents the Equality. Own Health Near dead Injured Normal Enemys Health Near dead Injured Normal RAP Weak Equal Strong RMS Slow Equal Fast

Table 1 Fuzzy Input Sets And the third step is defining these FISs membership functions.

Figure 10 Membership function for Own Health / Enemys Health which are normalized to 100 The figure above shows the membership function for Own Health as well as Enemys Health. As seen in figure, the health under 10 is definitely named like near dead and over 30 counts like Normal. The main reason for doing that is to prevent all the troops escape from the battle as all the troops should definitely fight if they are over 30 and they should try to escape if they are near dead. The figure below shows the RAP membership function. In this MF (membership function), equality is 50 and definitely stronger means 1.2 times stronger than the troop which is equal to 60 and definitely weaker means 1.2 time weaker than the troop which is equal to 46.6.

Figure 11 RAP Membership function

Figure 12 RMS Membership function On the other hand 1.1 times faster means definitely faster and 1.1 times slower means definitely slower. The tolerance is 10% to prevent the errors. If the tolerance is kept 20% than the flee consideration may not work as fifteen percent slower means no way to escape so it is better to keep the tolerance at 10%. And the last part is determination of rules. This part is the most important and most open part to make mistakes. In addition, the numbers of all combinations are. However it is not necessary to create all the rules for every possibility. In our system the rules are; 33x33=81 INPUTS Own Health Enemys Health RAP Not near dead All possibilities All possibilities near dead near dead near dead near dead near dead near dead near dead near dead OUTPUT Attack / Flee Attack Attack Attack Flee Flee Flee Flee Flee Flee

RMS All possibilities All possibilities All possibilities Slower injured equal Not faster near dead Weaker Not slower injured Weaker Not slower normal Weaker Not slower normal equal faster normal stronger faster injured equal faster

Table 2 Fuzzy Conditions for Attack or Flee If the troop is not heavily injured (not near dead) then it should continue attacking and shouldnt escape. The problem is if it is near dead since all the flee possibilities needs this

condition first. But even if the troop is near dead and slower than the enemy it should attack because there is no way to escape and the rest of the rules are easy to understand with the help of the table above. And the very last part is testing the fuzzy system with different data. All the data should start with the near dead condition or injured for Own Health since for the condition of normal, troop will definitely attack. One of the best examples is giving these values; Own Health Enemys Health RAP 9.38(near dead) 35.6(normal) 56.8(stronger) 9.38(near dead) 36.9(normal) 56.8(stronger) 8.38(near dead) 35.6(normal) 56.8(stronger) Table 3 Test decisions Although the only difference is enemys health with the difference of 1.3 the result changes and seems to be a good decision since if the enemy is weaker than there is a possibility to kill because it is stronger. And the next turn if the troop got closer to death than will definitely escape showed at the last line of the table above. RMS 53.1(faster) 53.1(faster) 53.1(faster) Result Attack Flee Flee

Figure 13 Decision is attack with the value of 51.1

Figure 14 - Decision is flee with the value of 49.6

ii.

Choosing Correct Troop to Attack

Another short term decision for individual troops in the RTS games is choosing correct troop to attack. This decision also is a short term decision since it is only related with an individual troop also in this part of this essay; Fuzzy Logic will be used to answer this question. The main reason for using Fuzzy Logic is the problem involves uncertainty and the solution should be deterministic. To give an example during a clash between two enemy groups lets assume that Team 1 has one troop and Team 2 has two troops and the troop in team 1 trying to determine which enemy troop to attack also lets assume that for each troop number of properties are three such as; health attack, power as well as armour. In this situation this troop should choose it according to degree of weakness of the enemy and this weakness should be calculated with the help of these troops properties. This explanation seems best fit to Fuzzy Logic to be used for determination. The FIS terms and the explanations for the hypothetical game scenario of this section are; OAP = Own Attack Power Own Effective Attack Power (OEAP) OAS = Own Attack Speed EAR = Enemys Armour EFH = Enemys Full Health EAP = Enemys Attack Power Enemys Effective Attack Power (EEAP) EAS = Enemys Attack Speed OAR = Own Armour OFH = Own Full Health

ECH = Enemys Current Health Enemys Health (EH) EFH = Enemys Full Health This variable normalized between [0-100] where 100 is healthiest. These equations differ from the equations in `Attack or Flee` section of this essay since while determining the correct troop to attack should be done according to individual attack power not group attack power. The main reason for doing that is, if the group power is calculated instead of individual power against an enemy troop we cannot really choose a weak enemy for our attacking skills. Another interesting point for this approach is this part doesnt include Own Health parameter since this section is not determining our attacking or fleeing decision this means that the decision of the troop should be best fitting decision for the weakness degree not our own health. After choosing FISs second part is creating the MF for these FISs.

Figure 15 Membership functions for Choosing Correct Troop to Attack Different from the Attack or Flee section, there are four MFs where healthy MF is new. The mean reason of putting the healthy parameter is increasing the precise for enemys health MF since it is really important for the decision calculation. The next step for creating our fuzzy logic is creating the output (FOS). The output membership graph consists of three possibilities as we need a precise output for this short term decision.

And the third step is creating rules. In this section, there are 36 possible combinations however it is reduced by using not operations as a result there are 15 combinations to implement, these are; OEAP strong strong not weak weak Inputs EH not healthy healthy near dead near dead EEAP All conditions All conditions not weak weak Output attack neutral attack neutral

not weak weak normal weak normal normal weak weak not weak weak

injured injured healthy healthy normal normal normal not near dead All conditions All conditions

All conditions All conditions All conditions All conditions strong not strong All conditions All conditions strong strong

attack attack neutral dont attack attack neutral dont attack neutral attack neutral

Table 4- Fuzzy rules for choosing correct troop to attack The main goal of these rules is attacking to the weakest in terms of its health and our attack power against this troop as well as the strongest enemy in terms of its attack power. After creating out fuzzy system the troop can choose the weakest enemy after the defuzzication operation.

Figure 16- Example for which troop to attack decision To give an example, lets suppose that there are three troops, first and second are from Circle Team and the third one is from Square Team (Figure 16). And the variables for the troop 3 against 2 and one are; Troop 1 EH 19 Troop 2 EH 7

OEAP 88

EEAP 88

OEAP 55

EEAP 95

Under these conditions, the troop is powerful against the troop 1 and health of troop 1 is bad but better than troop 2, however, troops 2s effective attack power is better than troop 1. So it is hard to determine since troop 2 is closer to dead but our attack power is not as strong as against troop1. But the fuzzy logic has an answer for both of the troops;

Output (result of defuzzication)

Troop 1 66.7

Troop 2 67

Also the results of the fuzzy logic are very close to each other as expected but there is a numerical result that we can decide according to. So the troop will attack to troop 2 as the output is bigger than troop 1s output.

Figure 17- Outputs for troop 1

Figure 18- Outputs for troop 2

b. Long Term Decisions in RTS Games

The easiest explanation for long term decisions in RTS games can be described as the decisions which affect all or a group of troops or buildings for a long time as well as can be considered as the management strategy of the game player. The best example for long term decisions is resource management during game play which means how many resource collectors (e.g. villagers, harvesters) should be created and ordered to collect certain types of resources. In addition to resource managements other examples for long term decisions are; determining correct buildings to build, achieving correct upgrades/technologies, choosing correct time to attack with full power etc. Not only for RTS games but also for any kind of game long term decision making always a big problem as the number of possibilities is may not be a certain value. Even if the numbers of possibilities are certain then possibilities and parameters are too much to make an easy decision. Moreover the difference between a short term decision and a long term decision is simply unreasonable short term decisions can be fixed in a short time however long term decision cannot be fixed so easily. For RTS games long term decisions are vital since the CCP (computer controlled player) should behave realistic, intelligent as well as shouldnt to not to frustrate the human player. The most common method for making these kinds of decisions are again the finite state machines which cause nearly a static game play. Every time the game player experiences the same game for the same map. To give an example in AOE2, at the end of the fourth minute, the CCP sends a scout to explore the map and creates a static number of villagers, orders them in a static way such as; four villagers hunt deer, ten of them collect food from trees etc., at the end of the seventh minute CCP attacks with a constant number of troops. This causes very static game scenario since the human player finds a way to repel the CCP and after the human player cannot be defeated by the CCP because the CCP cannot create any new way. The game producers of these RTS games usually create an AI with a static behaviour by using scripting languages. Therefore to create a strong opponent against the human player they prefer using cheating methods such as gifting new troops as well as resources which frustrates the human player. To create a realistic behaviour for CCPs, which means intelligent and learnable behaviour, some other methods should be used such as ANN since it provides learning for CCPs. In addition to this ability of ANNs, ANNs may also provide un-deterministic behaviour by integrating GA (Genetic Algorithm). However, this method consumes lots of CPU time and provides a very slow learning. This section of this paper will recommend using ANN (artificial neural networks) for long term decision making by giving some basic ideas such as defining input layer parameters for ANN and the outputs as well. However, all the recommendations are hypothetical since none of the ideas are based on any calculations or experiment. For these hypothetical recommendations the famous RTS game AOE2 (Age of Empires 2) will be used as the RTS game environment.

i.

ANN Structure and Hypothetic Feeding Mechanism of the ANN

As mentioned before on this paper, an ANN structure consists of three fundamental elements; inputs, weights and outputs. In our system inputs are the numerical values of a relevant system such as; for resource management system first input can be the recourse (e.g. gold, wood) the player has and the outputs are actions such as; create villager or send a villager to collect gold.

Figure 19 An ANN Module As mentioned before, the training method for the RTS AI is back propagation which is a supervised learning method and the weight calculations are not dynamic. This means the calculation of weights can be done after the game play. To reduce the calculations and to separate behaviours, the module approach is preferred to be used. To give an example from our conceptual game AOE2, behaviour of the CCP during dark-age in terms of resource collection should be different from castle age. Instead of using the current age as an input value for the AI, creating different ANN modules can be another approach. This also provides parallel calculations for server-side such as calculation of dark- age could be made separately from the calculation of castle age by using threads. Another benefit of this approach is the success of each module can be send to server as training data if it fits the necessary criteria such if the player achieves castle age before computer this data can be send to the server even if the player losses the game. However, determination of the criteria should be search carefully to not to train the AI with novel data.

Figure 20 Before games start all weights getting from AI server To load the weights of the game AI, the client should connect to the AI server and should get the trained ANNs weights to provide a better and dynamic game play. This method can be another approach for reducing piracy in games like, if the player uses a pirate version of the game cannot download the last AI weights since to download the AI data server can request for the player ID and password first. Also the game AI server should contain trained and tested data before release of the game AI since, no one wants to play with a dummy AI. So the game company should be well trained the game AI modules which can be a problem for the game development.

Figure 21 At the end of each game all input and outputs sending to AI server for calculation of weights if the result of the game is successful Briefly the steps of this system are; For AI loading; 1. Connect to AI server 1. Check for ID, Password 2. Send weights if successfully connected 3. Create the local AI with new weights 4. If cannot connect 1. Use the previous ANN weights. For data collection (collecting the training data); 1. For every action 1. Collect input variables of the relevant AI module 2. Collect the action 3. If the current ANN module reaches the criteria to be changed 1. Change the ANN module 2. If the ANN training data reaches the criteria, mark to be sent to server 3. Else dont mark and dont discard the ANN training data set 4. At the end of the game 1. Send all ANN training data sets of the winners. 2. Send all the marked ANN training data sets. For Server Side Weight calculations; 1. If there is new data, 1. join all the data of relevant ANN modules including new data and old data 1. i. Create threads for every ANN module 2. ii. Calculate until reaching a threshold for every ANN module

3. If there is no new data, 1. Define threshold values lower than the old threshold values 1. i. Create threads for every ANN module 2. ii. Calculate until reaching a threshold for every ANN module

ii.

Example ANN Structure 1: Resource Management in Dark Age

To create the ANN structure first of all the input values should be determined. In a RTS game for resource management can be the number of resources, number of troops collecting the resources. For our example game AOE2, the input values for dark-age can be chosen like; 1. Number of workers 2. Number of workers collecting food 3. Number of workers collecting wood 4. Number of workers collecting gold 5. Number of workers collecting stone 6. Amount of wood we have 7. Amount of wood we have 8. Amount of gold we have 9. Amount of stone we have 10. Race of the side (such as Aztecs, Goths, Turks etc.) And the outputs of the ANN module are decisions such as; 1. Create villager 2. Send a villager from food to wood 3. Send a villager from food to gold 4. Send a villager from food to stone 5. Send a villager from wood to food

6. Send a villager from wood to gold 7. Send a villager from wood to stone 8. Send a villager from gold to food 9. Send a villager from gold to wood 10. Send a villager from gold to stone 11. Send a villager from stone to food 12. Send a villager from stone to wood 13. Send a villager from stone to gold The data collection in the game should be triggered by the action such as, if the player choose a villager from stone collection and send him to wood collection than all the input data and should be collected after the worker starts working. At the same time another module is working for achieving technologies and if the resources are enough to pass the next age than all the data should be recorded according to the algorithm mentioned before.

iii.

Example ANN Structure 2: Deciding the Correct Troops to Create

This part can be a either fuzzy logic or ANN since it seems like a spontaneous action, however the number of variable makes the fuzzy logic nearly impossible to implement this part and also actually this decision is not only spontaneous but also effects the game in long term as creating of Paladin is as expensive as achieving some technologies. The input variables can be; 1. 2. 3. 4. 5. 6. 7. 8. 9. Number of own archers Number of own knights Number of own swordsmen Number of own skirmishers Number of own special troops Number of own other troops Number of own defensive buildings Number of enemys archers Number of enemys knights

10. Number of enemys swordsmen

11. Number of enemys skirmishers 12. Number of enemys special troops 13. Number of enemys other troops 14. Number of enemys defensive buildings 15. Score of the enemy (this variable provided by the AOE2 game environment) 16. Own score 17. Own race 18. Enemys race 19. Amount of wood we have 20. Amount of wood we have 21. Amount of gold we have 22. Amount of stone we have Outputs are decisions again; 1. 2. 3. 4. 5. Create archer Create knight Create swordsman Create skirmisher Create special troop

As seen above, the numbers of inputs are pretty much since it is really hard to determine even for human instinct which troop to create that makes the game interesting and keeps players passions on the game. Therefore if this system really can be implemented and reaches a degree of success than games lifetime for players definitely will be longer as most of the strategy game players play strategy games for the game AI not only for graphics.

Conclusion
Artificial intelligence is the most important for strategy games and especially for real time strategy games since the computer controlled opponents should make reasonable decisions spontaneously. For most of the strategy games, game producers preferred the easy way; cheating in different ways such as giving new troops, increasing income rate providing from resources and other similar ways, however results of these methods never

satisfied the game players. The most important reason for that is; when the human player finds a way to defeat the computer, by using the same patterns (tactics), the human player never lose again. Briefly human player can learn but the computer cannot. Actually they can but this method never tried in commercial strategy games. There are several reasons behind that; first of all the CPU intensity of the learning structure, secondly the success rate is not known as the learning method hardly used in games. Not only machine learning but also spontaneous decision making, in most of the strategy games, is poor. Actually these short term decisions can be made with fuzzy logic and in some of the new strategy games it seems to be used (Command Conqueror Tiberium Wars) for choosing correct troop to attack, however it is not definite since no explanation have been made about the game AI for this game. At first sight the implementation of fuzzy logic could be seem like simple especially for the short term decision making, however, the exponentially increasing number of possibilities makes hard the fuzzy logic to be implemented. On the other hand, in this paper, the tested short term decisions seem working. Especially choosing correct troop in the range to attack seems to be a successful application of fuzzy logic according to test results but without a real time application it is not reasonable to judge as a successful application of fuzzy logic since CPU usage is not known. The conceptual distributed server based ANN application hasnt tried yet by any game. Besides this kind of distributed approach havent tried for any kind of game AI yet. The CPU usage problem of the ANN is a known weak point of this structure. Another weak point of ANNs is the requirement for huge number of feed data (training). This conceptual distributed system may be a key for solution of these problems. Additionally, this trained AI structures can have a commercial value since they can decrease the number of pirate usage as the strategy game players always want to play with a more intelligent opponent and most of them will want to be registered to the AI service provider this means preventing piracy. As a result, the problems about short term decision making and also long term decision making tried to be solved by using ANNs and Fuzzy Logic but none of the approaches has been tried in a real time game. However, the results for fuzzy logic seem to fit like a glove the given problem. On the other hand the conceptual ANN distributed system can be a new approach for solving the problems of ANNs in RTS games.

References
[1] David M. Bourg & Glen Seemann, AI for Game Developers, July 2004, First Edition, OReilly [2] Mat Buckland & Andre LaMothe, AI Techniques for Game Programming, 2002, Premier Press [3] Mat Buckland, Programming Game AI by Example, 2005, Wordware Publishing Inc.

[4] Todd Barron, Strategy Game Programming with DirectX 9.0, 2003, Wordware Publishing Inc. [5] Mark A. DeLoura (edited by), Game Programming Gems, 2000, Charles River Media [6] Mark A. DeLoura (edited by), Game Programming Gems 2, 2001, Charles River Media [7] Steve Rabin (edited by), AI Game Programming Wisdom, 2002, Charles River Media [8] T.J.A. Jansen, Player Adaptive Cooperative Arti_cial Intelligence for RTS Games, June 13, 2007, http://www.cs.unimaas.nl/~uiterwyk/Theses/BSc/Jansen_BSc-paper.pdf, last visit date: 30-11-2007 [9] Michael Chung, Michael Buro, and Jonathan Schaeffer, Monte Carlo Planning in RTS Games, http://www.cs.ualberta.ca/~mburo/ps/mcplan.pdf, visit date: 30-11-2007 [10] F.C. Schadd, June 13 2007, Hierarchical Opponent Models for Real-Time Strategy Games http://www.cs.unimaas.nl/~uiterwyk/Theses/BSc/Schadd_BSc-paper.pdf, visit date: 30-11-2007 [11] Daniel Johnson and Janet Wiles, Computer Games with Intelligence, http://www.itee.uq.edu.au/~uqdjohns/publications/AI/AJIIPS_AI.pdf, visit date: 30-112007 [12] Wikipedia, Artificial_neural_network, http://en.wikipedia.org/wiki/Artificial_neural_network, last visit date: 30-11-2007 [13] Wikipedia, Fuzzy Logic, http://en.wikipedia.org/wiki/Fuzzy_logic, last visit date: 30-11-2007 [14] Dr Emma Hart, Lecture Notes; Introduction to Neural Networks, 13-04-2005, http://www.soc.napier.ac.uk/module.php3? op=getlecture&cloaking=no&lectureid=365774, last visit date: 30-11-2007 [15] Christos Stergiou and Dimitrios Siganos, NEURAL NETWORKS, http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html#Why%20use %20neural%20networks, last visit date: 30-11-2007 [16] Stuart James Kelly, Applying Artificial Intelligence, Search Algorithms and Neural Networks to Games, 2003, http://www.generation5.org/content/2003/KellyMiniPaper.asp, last visit date: 30-11-2007

[17] Artificial Neural Networks, 1999, http://www.psych.utoronto.ca/users/reingold/courses/ai/nn.html, last visit date: 30-112007 [18] Artificial Intelligence in Games , 17 Jul 2006, http://www.codeproject.com/KB/architecture/aigame.aspx, last visit date: 30-11-2007