Approaches and Systems

Lecture 1
Chapter 1 Introduction

Prof. Hongguang Li
Beijing University of Chemical Technology
 Who am I ?

Hongguang LI
P f
Professor
Intelligent
g Process Control

Offi Room
Office: R 617,
617
Science & Technology Building, BUCT
Tel: 010-64434797
a : lihg@mail.buct.edu.cn
E-mail: g@ a .buc .edu.c
1
 Research interests
Industrial process modeling
modeling, computer control
control,
monitoring and optimization;
Intelligent control and evolutionary computations;
Intelligent decision
decision-making
making

Teachingg
Process Control Engineering (for undergraduates)
Intelligent Control (for graduates)
Artificial Intelligence (for graduates)
2
 Chapter 1 Introduction

1.1 Course Schedules

1.2 AI Concepts
1.3 The History of AI
1.4 AI Applications

3
 Ch t 1 IIntroduction
Chapter t d ti
1 1 Course
1.1 C S
Schedules
h d l

Objectives
Artificial intelligence (AI) which concerns the
intelligence of machines is a branch of computer
science that aims to create it.
it
This course is aiming at providing with a detailed
coverage of artificial intelligence theory and
gy from an engineering
technology g gpperspective.
p
4
 Organizations

Chapter 1 Introduction
Course schedules; AI Concepts; The history of AI; AI
Applications
pp
Chapter 2 Problem-Solving
Knowledge Basics; General Problem Solving; State-
space Graphs & Searches; Problem Reductions;
Intelligent Agents
5
Chapter 3 Logic and Reasoning
Introduction;; Propositional
p logic;
g ; Predicate logic;
g ;
AI programming languages
Chapter 4 Fuzzy Systems
IIntroduction;
t d ti F
Fuzzy sets;
t Fuzzy
F R l ti
Relations; F
Fuzzy
inference; Fuzzy Rule-bases
Chapter 5 Artificial Neural Networks
Introduction; Feed-forward networks; Feed-back
networks
6
Chapter 6 Rule-based
Rule based Expert Systems
Introduction;; ES architectures;; Knowledge
g
representations; Inference engines
Chapter 7 Machine Learning
I t d ti
Introduction; L
Learning
i from
f examples;
l Data
D t mining
i i
Chapter 8 Evolutionary Computations
Introduction; Genetic Algorithms; Detailed Gas;
Realizations of Gas; Extensions of Simple GA; GA
Application Areas
7
 References
Stuart J. Russell, Artificial Intelligence: A modern
pp
Approach
Michael Negnevitsky, Artificial Intelligence: A
G id to
Guide t Intelligent
I t lli t Systems
S t

Grade Points
Final exam 60%, Homework + Seminars 40%.

8
Seminar 1.1

1. Why do you attend the course of AI

2. Do you have any knowledge or experience on

AI ?

9
 Chapter 1 Introduction

1.1 Course Schedules

1.2 AI Concepts
1.3 The History of AI
1.4 AI Applications

10
1.2 AI Concepts

For thousands of years, we have tried to understand how

we think: that is, how a mere handful of matter can
perceive, understand, predict, and manipulate a world
f larger
far l andd more complicated
li d than
h itself.
i lf

Views of AI fall into four categories:

Thinking humanly Thinking rationally
Acting humanly Acting rationally
11
 Acting humanly: Turing Test

Turing (1950) "Computing machinery and

intelligence":
g "Can machines think?" "Can machines
behave intelligently?"
O
Operational
ti l test
t t for
f intelligent
i t lli t behavior:
b h i th Imitation
the I it ti
Game

12
 Acting humanly: Turing Test

Predicted that by 2000, a machine might have a 30%

chance of fooling a lay person for 5 minutes
Anticipated all major arguments against AI in
following 50 years
Suggested major components of AI: knowledge,
reasoning,
g, language
g g understanding, g, learningg

13
 Thi ki humanly:
Thinking h l cognitive
i i modeling
d li

1960s "cognitive
cognitive revolution
revolution":: information-processing
information processing
psychology
Requires scientific theories of internal activities of the
brain
-- How to validate? Requires
1) Predicting and testing behavior of human subjects
(top-down) or
2) Direct identification from neurological data
(bottom-up)
Both approaches (roughly, Cognitive Science and
Cognitive Neuroscience) are now distinct from AI
14
 AI Definitions

Artificial intelligence (AI) which concerns the

intelligence of machines is a branch of computer
science that aims to create it.

AI, broadly defined, is concerned with intelligent

behaviors in artifacts.
artifacts

Intelligent
g behaviors,, in turn,, involve p
perception,
p ,
reasoning, learning, communicating, and acting in
complex environments.
environments
15
AI has as one of its long-term goals the
development of machines that can do these things as
well as human can, or possibly even better.

Another goal of AI is to understand this kind of

behavior whether it occurs in machines or humans
or other animals.
animals

Thus AI has both engineering and theory goals.

Thus, goals

16
 AI Paradigms

(1) Symbolism (Newell and Simon, 1976)

An AI system consists of a set of symbols.
symbols A physical
symbol system has the necessary and sufficient means
for general intelligent actions.
actions (ES)

(2) Connectionism (McClelland and Rumelhart, 1986)

It aims at massivelyy pparallel models that consist of a
large number of simple and uniform processing
elements interconnected with extensive links. (NN)
17
Seminar 1.2

1. Define in your own words: (a)intelligence.

(b) artificial
tifi i l intelligence.
i t lli

22. Please talk about

abo t the difference between
bet een AI
symbolism and connectionism.

18
 Chapter 1 Introduction

1.1 Course Schedules

1.2 AI Concepts
1.3 The History of AI
1.4 AI Applications

19
1 3 The History of AI
1.3

AI Prehistory
Philosophy: Logic, methods of reasoning, mind as
physical system foundations of learning,
language rationality
language,
Mathematics: Formal representation and proof
algorithms, computation, (un)decidability,
((in)tractability,
) y, pprobabilityy
Economics: utility, decision theory
N
Neuroscience:
i physical
h i l substrate
b t t forf mental t l activity
ti it
20
Psychology : phenomena of perception and motor
control, experimental techniques
C
Computer engineering
i i :
building fast computers
Control theory: design systems that maximize an
objective function over time
Linguistics: knowledge representation, grammar

21
 Abridged history of AI

1943 McCulloch & Pitts: Boolean circuit model of brain

1950 TTuring's
i ' "C"Computing
ti MMachinery
hi andd IIntelligence"
t lli "
1956 Dartmouth meeting: "Artificial Intelligence"
adopted
1950s Early AI programs,
programs including Samuel
Samuel'ss checkers
program, Newell & Simon's Logic Theorist,
Gelernter's Geometry Engine

22
1965 Robinson's complete algorithm for logical
reasoning
1966-73 AI discovers computational complexity
Neural network research almost disappears
1969-79
1969 79 Early development of knowledge
knowledge-based
based systems
1980-- AI becomes an industry
1986
1986-- N
Neurall networks
k return to popularity
l i
1987-- AI becomes a science
1995-- The emergence of intelligent agents

23
Alan Turing proposed an imitation game (1950)

-- terminal communication with an unknown partner

-- no way of identifying the partner
-- Question: is the partner human or not?
On the internet, nobody knows you are a dog!
New Yorker Magazine, July 1993
24
 St t off the
State th artt
Deep Blue defeated the reigning world chess champion Garry
Kasparov in 1997
Proved a mathematical conjecture (Robbins conjecture) unsolved
for decades
No hands across America (driving autonomously 98% of the time
f
from Pitt
Pittsburgh
b h tot San
S Diego)
Di )
During the 1991 Gulf War, US forces deployed an AI logistics
planning and scheduling program that involved up to 50,000
50 000
vehicles, cargo, and people
NASA'ss on-board autonomous planning program controlled the
NASA
scheduling of operations for a spacecraft
Proverb solves crossword puzzles better than most humans
25
 Chapter 1 Introduction

1.1 Course Schedules

1.2 AI Concepts
1.3 The History of AI
1.4 AI Applications

26
1.4 AI Applications

Natural Language Processing

27
NLP is concerned with the interactions between
computers
t and
d human
h ( t l) languages,
(natural) l and,
d in
i
particular, concerned with programming computers to
fruitfully process large natural language corpora.

Challenges in natural language processing frequently

involve natural language
g g understanding, g, natural language
g g
generation (frequently from formal, machine-readable
l i l forms),
logical f ) connecting
ti l
language andd machine
hi
perception, dialog systems, or some combination thereof.
28
 Theorem Proving

29
Automated theorem proving (also known as ATP
or automated deduction) is a subfield of automated
reasoning and mathematical logic dealing with
proving mathematical theorems by computer
programs.
Automated reasoning over mathematical proof was a
major impetus for the development of computer
science.
science

30
 Vision Systems

31
 Vision Systems

Vision system may refer to:

Visual system (the neurobilogical circuitry and
processing that enable living beings to see)
artificial Vision Systems (computer based systems
where software pperforms tasks assimilable to "seeing",
g
usually aimed to industrial quality assurance, part
selection defect detection etc.).
selection, etc )
Computer vision
32
 Problem Solving

33
 Problem Solving

Problem solving consists of using generic or ad hoc

methods, in an orderly manner, for finding solutions
to pproblems. Some of the pproblem-solvingg
techniques developed and used in artificial
intelligence
intelligence, computer science,
science engineering
engineering,
mathematics, or medicine are related to mental
problem-solving techniques studied in psychology.

34
 Automatic Programming

35
 Automatic Programming

In computer
p science,, the term automatic
programming identifies a type of computer
programming in which some mechanism generates
a computer program to allow human programmers
to write the code at a higher abstraction level.

36
Seminar 1.3

Please present an AI application which you are

f ili with.
familiar ith

37
Homework 1

1. Please describe Turings imitation game in details.

2. Examine
2 E i the
th AI literature
lit t t discover
to di whether
h th the
th
following tasks can currently be solved by computers.
a. Playing a decent game of table tennis
b Driving
b. D i i in
i the
h center off a city
i
c. Buying a week
weekss worth of groceries on the Web.
d. Writing an intentionally funny story
38