Artificial Intelligence/Intelligent

Machine
• Human beings and animals are Intelligent or have the
• Ability to show intelligent behavior/characteristics.
But
• Can it be created Artificially?
• Can we put intelligent behavior into machine?
• Can we feed intelligent characteristics into machine?
IF YES
Artificial Intelligence/Intelligent Machine
 Artificial Intelligence/Intelligent
Machine
• What if????
• A machine searches through a mesh and finds a path?
• – A machine solves problems like the next no. in the
• sequence?
• – A machine develops plan?
• – A machine answers ambiguous questions?
• – A machine diagnoses and prescribes?
• – A machine recognize fingerprints?
• – A machine understand?
• – A machine perceives?
• – A machine behaves as HUMANS DO?
 Purposes of AI
• To use the power of computers to enhance
human thinking (A biased view). To use a
computer's artificial intelligence to understand
how humans think.
• – In a humanoid way. If you test your programs
not merely by what they can accomplish, but how
they accomplish it, then you're really doing
cognitive science; you're using AI to understand
the human mind.
Herbert Simon
 Fundamental Definition of AI
• No comprehensive definition
• The study of how to make computer do things
which at the moment humans do better.
Or
• Can we make computer /machine better than
human beings when they perform some sort
of actions.
 How we can automate computer
• How can we bring computer = human
• How brain works
• Brain story
– Logic or deduction
– Logical sequence of reasoning, if else approach
– Problem solving mechanism in brain
– How we see the things
– Where we place
– Working consciously
– Perception
– Recognition
– And if succeed how brain does it
• We can easily automate our computer/machine
 Intelligent Behavior

• Intelligent behavior mean to perceive one environment

• To act in complex environment
• To learn and understand of experience
• To communicate with others
• To think abstract using analogies
• Intelligent behavior also includes creativity, curiosity, expressiveness etc
 Formal Definition of AI
• Views of AI fall into four categories:
• Two schools of thought

Thinking Humanly Thinking Rationally

Acting Humanly Acting Rationally

 Formal Definition of AI
• System that thinks like human
– The exciting new effort to make computers think….machine with minds, in the
full and literal
– The automation of activities that we associate with humans thinking, activities such as
decision making, problem solving
– The study of mental faculties through the use of computational models
– The study of computation that makes it possible to perceive reason and act
• System that acts like human
– The art of creating machine that performs functions that requires intelligence
when performed by people
– The study of how to make computers do things at which at the moment people are
better
– A field of study that seeks to explain and emulate intelligent behavior in terms
of computational process
– The branch of computer science that is concerned with the automation of intelligent
behavior
 Two Schools of Thought
• We go inside the brain and see how it is
thinking, and doing, e.g. toy and baby
• Monitor brain activity like a block box, and try
to replicate/copy
• Both of these school of thought fall into
another aspect of AI
– Strong AI
– Weak AI
 Thinking Humanly
• Can machines think like humans
– Think like humans (human‐like patterns of
thinking steps)
• Requires scientific theories of internal
activities of the brain, psychological
experiments are required
• Studied in Cognitive Modeling
– Modeling exactly how humans actually think
and reason
Thinking Humanly: Cognitive Modeling
• Cognitive Science
– Brings together computer models from AI and
experimental techniques form psychology in
order to try to construct precise and testable
theories of the working of the human mind.
 Thinking Rationally
• A system is rational if it does the right things.
• Laws of Thought approach
• Can machines think rationally?
 Thinking Rationally
• Aristotle: one of the first to codify right thinking,
which is actually a reasoning process.
– E.g. “Saira is a girl”, all girls are mortal , therefore
Saira is mortal.
• These laws of thought were supposed to govern
the operation of mind
• And initiated the field of LOGIC, which provides a
precise notation for statement about all kinds in
the world and the relation between them
 Turing Test
• The machine would need to possess the
following capabilities, to pass the test.
– Natural language processing
– Knowledge representation & reasoning
– Automated reasoning
– Machine Learning
 Problems:
• What is the purpose of thinking? What
thoughts should I have?
• Difficult to state informal knowledge into
formal terms required by logical notation.
• Big difference between solving a problem in
“principle”, and doing so in practice.
• A reference;
– Ivan Bratko, Prolog programming for artificial
intelligence.
 Acting Humanly
• Can machines behave like Humans?
• Why and How is not important do what ever
you can

• The test he proposed is that the computer

should be interrogated by a human through a
teletype, and passes the test if the
interrogator can not tell if there is a computer
or a human at the other end.
Acting Humanly: Turing Test
 General AI Goals
1. To replicate human intelligence.
2. To make an intelligent connection between action and perception
3. To enhance the interaction between human to human, human to
computer and computer to computer
Science based goal
 To develop concept, mechanisms and vocabulary to understand
biological intelligent behavior
 The emphasis of science based AI goal is on understanding intelligent
behavior.
Engineering based goal
 To develop concepts, theory and practice of building intelligent machine.
 The emphasis on engineering based AI goal is on system building
 Application of AI
• Game playing
• Game play is a search problem defined by
 Initial state-board
 Expand function-build all successor states
 Cost function-payoff of the state
 Goal test-ultimate state with maximum payoff
• Game playing characterized by
 Unpredictable opponent
 Need specify move for every possible opponent reply
 Time limit
 Application of AI
• Computer games
 Champion level game, chekers, chess, othello
 Computer perform well game, example:bridge
 Computer still do badly, example: Go, Hex
• Speech Recognition
 Voice dialing
 Call routing
 Data entry
 Speaker recognition
 Application of AI
• Understanding Natural Language
• Natural language processing (NLP): does automated generation and
understanding of natural human languages.
 NLGS: convert information from computer databases into normal-
sounding human language
 NLUS: covert sample of human language into more formal representation
that are easier for computer programs to manipulate
• Some major tasks in NLP
• Text to speech (TTS) system:
• Speech recognition (SR) system:
• Machine translation (MT) system:
• Information retrieval (IR) system:
 Application of AI
• Computer vision
 Handwriting recognition
 Baggage inspection
 Manufacturing inspection
 Photo interpretation

• Expert system
 Diagnosis and troubleshooting
 Planning and scheduling
 Financial Decision Making
 Process Monitoring and control

• Heuristic classification
 Major components of AI
1. User Interface
2. The Knowledge Base
3. The Shell or Interface Engine

• Machine Learning
• Machine learning refers to a system capable of acquiring and integrating the
knowledge automatically.

• The capability of the system to learn from experiences, training, analytical

observation, and other means.

• Results in a system that can continuously self-improving

• Exhibit efficiency and effectiveness
 Machine Learning

• Components of Machine Learning

1. Learning element
2. Knowledge base
3. Performance element
4. Feedback element
5. Standard system
• Several factors affecting the performance
• Types of training provided
• The form and extend of any initial background knowledge
• The type of feedback provided
• The learning algorithms used
 History of AI
• 1943 McCulloch & Pitts: Boolean circuit model of brain
• 1950 Turing's "Computing Machinery and Intelligence"
• 1956 Dartmouth meeting: "Artificial Intelligence" adopted
• 1952‐69 Look, Ma, no hands!
• 1950s Early AI programs, including Samuel's checkers program, Newell &
Simon's Logic Theorist,
• Gelernter's Geometry Engine
• 1965 Robinson's complete algorithm for logical reasoning
• 1966‐73 AI discovers computational complexity Neural network research
almost disappears
• 1969‐79 Early development of knowledge‐based systems
• 1980‐‐ AI becomes an industry
• 1986‐‐ Neural networks return to popularity
• 1987‐‐ AI becomes a science
• 1995‐‐ The emergence of intelligent agents