Artificial Intelligence

Syllabus
 Course Description

 This course provides a general introduction

to AI (Artificial Intelligence): Its techniques
and its main sub-fields.

 It gives an overview of underlying ideas,

such as search, knowledge representation,
expert systems and learning.
2
Syllabus
 Recommended Books:

1. “Artificial Intelligence – Structures and Strategies for

Complex problem solving”,George F. Luger, Pearson
International Edition, Sixth edition,

2. “Artificial Intelligence: A modern approach” Stuart Russell,

Peter Norvig, Prentice Hall, (latest edition)

3. “Artificial Intelligence Illuminated” Ben Coppin,

Jones and Bartlett illuminated Series

3
Syllabus
 Course Overview (main topics)

 What is AI?
 problem solving by search
 logic, knowledge representation & reasoning
 expert systems: an introduction
 learning: decision trees, artificial neural networks,
reinforcement learning
 Game playing

4
What is Artificial Intelligence?
What is Intelligence ?

 Intelligence may be defined as:

1. The capacity to acquire and apply

knowledge.

2. The faculty of thought and reason.

6
What is Artificial Intelligence ?
 Artificial intelligence is the study of systems that act
in a way that to any observer would appear to be
intelligent.

 Artificial Intelligence involves using methods based

on the intelligent behavior of humans and other
animals to solve complex problems.

 AI is concerned with real-world problems (difficult

tasks), which require complex and sophisticated
reasoning processes and knowledge.

7
What is Artificial Intelligence ?
 “AI is the study of ideas that enable
computers to be intelligent.”

[P. Winston]

 “It is the science and engineering of

making intelligent machines,
especially intelligent computer
programs. It is related to the similar
tasks of using computers to understand
human intelligence, but AI does not
have to confine itself to methods that
are biologically observable.”
John McCarthy
John McCarthy, Stanford University,
computer Science Department.

8
What is Artificial Intelligence?
 Some Definitions

 Weak AI: AI develops useful, powerful

applications.

 Strong AI: claims machines have cognitive minds

comparable to humans.

 In this course, we deal with Weak AI.

9
What is Artificial Intelligence?
 Operational Definition of AI
(Turing Test):

In 1950 Turing proposed an

operational definition of intelligence by
using a Test composed of :

 An interrogator (a person who will ask

questions)
 a computer (intelligent machine !!)
 A person who will answer to questions
 A curtain (separator) A. Turing

10
 What is Artificial Intelligence?

The computer passes the “test of intelligence” if a human, after

posing some written questions, cannot tell whether the responses
were from a person or not.
11
What is Artificial Intelligence
 To give an answer, the computer would need to
possess some capabilities:

 Natural language processing: To communicate successfully.

 Knowledge representation: To store what it knows or hears.
 Automated reasoning: to answer questions and draw
conclusions using stored information.
 Machine learning: To adapt to new circumstances and to
detect and extrapolate patterns.
 Computer vision: To perceive objects.
 Robotics to manipulate objects and move.

12
What is Artificial Intelligence ?
Goals of AI:

AI began as an attempt to understand the nature of

intelligence, but it has grown into a scientific and
technological field affecting many aspects of commerce
and society. The main goals of AI are:

 Engineering: solve real-world problems using

knowledge and reasoning. AI can help us solve
difficult, real-world problems, creating new
opportunities in business, engineering, and many other
application areas
13
What is Artificial Intelligence ?
Goals of AI (cont’d)

 Scientific: use computers as a platform for studying

intelligence itself. Scientists design theories
hypothesizing aspects of intelligence then they can
implement these theories on a computer.

Even as AI Technology becomes integrated into the fabric

of everyday life. AI researchers remain focused on the grand
challenges of automating intelligence.

14
What is Artificial Intelligence ?
Examples of AI Application
systems:

 Game Playing
 TDGammon, the world champion
backgammon player, built by Gerry
Tesauro of IBM research

 Deep Blue chess program beat world

champion Gary Kasparov

 Chinook checkers program

15
What is Artificial Intelligence ?
Examples of AI Application systems:

 Natural Language Understanding

 AI Translators – spoken to and prints what

one wants in foreign languages.

 Natural language understanding (spell

checkers, grammar checkers)

16
What is Artificial Intelligence ?
Examples of AI Application Systems:

 Expert Systems:

 In geology

• prospector expert system carries evaluation of mineral potential of

geological site or region

 Diagnostic Systems

• Pathfinder, a medical diagnosis system (suggests tests and makes

diagnosis) developed by Heckerman and other Microsoft research

• MYCIN system for diagnosing bacterial infections of the blood and

suggesting treatments

17
What is Artificial Intelligence ?
Examples of AI Application Systems:

 Expert Systems:

 Financial Decision Making

• Credit card providers, banks, mortgage companies use AI systems to

detect fraud and expedite financial transactions.

 Configuring Hardware and Software

• AI systems configure custom computer, communications, and

manufacturing systems, guaranteeing the purchaser maximum
efficiency and minimum setup time.

18
What is Artificial Intelligence ?
Examples of AI Application Systems:

 Robotics:

 Robotics becoming increasing important in various areas like: games, to handle

hazardous conditions and to do tedious jobs among other things. For examples:
- automated cars, ping pong player

- mining, construction, agriculture

- garbage collection

19
What is Artificial Intelligence ?
Examples of AI Application systems:

 Other examples:

 Handwriting recognition (US postal service zip code readers)

 Automated theorem proving

• use inference methods to prove new theorems

 Web search Engines

20
Artificial Intelligence History
Early AI: (The gestation of Artificial Intelligence)

1943 McCulloch & Pitts: Boolean circuit model of brain

1950 Turing's ``Computing Machinery and Intelligence''
1950s Early AI programs, including Samuel's checkers
program,
Newell & Simon's Logic Theorist, Gelernter's Geometry
Engine

The birth of Artificial Intelligence (1956)

1956 McCarthy organizes Dartmouth meeting and includes

Minsky, Shannon, Newell, Samuel, Simon

Name ``Artificial Intelligence'' adopted 21

Artificial Intelligence History
Early enthusiam, great expectations (1952-1969):

1957 General Problem Solver [Newell, Simon, Shaw @ CMU]

1958 Creation of the MIT AI Lab by Minsky and McCarthy
1958 LISP, [McCarthy], second high level language (MIT AI Memo
1)
1963 Creation of the Stanford AI Lab by McCarthy
1965 Robinson's complete algorithm for logical reasoning

A dose of reality (1966-1973):

1966-74 AI discovers computational complexity …

1966-72 Shakey, SRI’s Mobile Robot [Fikes, Nilson]

22
Artificial Intelligence History
Knowledge-based systems (1969-1979)

1969 Publication of “Perceptrons” [Minsky & Papert],

Neural network research almost disappears
1969-79 Early development of knowledge-based systems
1970 SHRDLU, Winograd’s natural language system
1971 MACSYMA, an symbolic algebraic manipulation system

AI becomes an Industry (1980 – present)

1980-88 Expert systems industry booms

1981 Japan: Fifth generation project
US: Microelectronics and Computer Technology Corp.
UK: Alvey

23
Artificial Intelligence History
The return of neural networks (1986 - present)

1988-93 Expert systems industry busts: ``AI Winter''

1985-95 Neural networks return to popularity

AI becomes a science (1987 – present)

1988- Resurgence of probabilistic and decision-theoretic methods

Computational learning theory

``Nouvelle AI'': ALife, GAs, soft computing, emergent computing …

Complex Systems or the Science of complexity

24
AI Topics:
A Quick Introductory Overview
The main AI topics we’ll cover in this introductory
course:

 Problem solving by searching

(Uninformed search, heuristic search …)
 Knowledge-based systems
(expert systems …)
 Machine learning
(neural networks, RL …)
 Artificial Life <Modern AI>
(cellular automata, GAs …)

25
AI Topics:
A Quick Introductory Overview
Problem Solving by Searching

Why search ?

 Early works of AI was mainly towards

• proving theorems
• solving puzzles
• playing games

 All AI is search!

 Not totally true (obviously) but more true than you might think.
 Finding a good/best solution to a problem amongst many possible
solutions.

26
AI Topics:
A Quick Introductory Overview
Classic AI search problems
 Map searching (navigation)

27
AI Topics:
A Quick Introductory Overview
Classic AI search problems
 3*3*3 Rubik’s Cube

28
AI Topics:
A Quick Introductory Overview
Classic AI search problems
 8-Puzzle

2 1 3 1 2 3
4 7 6 4 5 6
5 8 7 8

29
AI Topics:
A Quick Introductory Overview
Knowledge-based system
 expert system (or knowledge-based system): a program
which encapsulates knowledge from some domain,
normally obtained from a human expert in that domain

 components:
 Knowledge base (KB): repository of rules, facts
(productions)
 working memory: (if forward chaining used)
 inference engine: the deduction system used to infer
results from user input and KB
 user interface: interfaces with user
 external control + monitoring: access external databases,
control,...

30
AI Topics:
A Quick Introductory Overview
Knowledge-based system
 Why use expert systems:

 commercial viability: whereas there may be only a few experts whose time
is expensive and rare, you can have many expert systems
 expert systems can be used anywhere, anytime
 expert systems can explain their line of reasoning
 commercially beneficial: the first commercial product of AI

 Weaknesses:

 expert systems are as sound as their KB; errors in rules mean errors in
diagnoses

 automatic error correction, learning is difficult (although machine learning

research may change this)

 the extraction of knowledge from an expert, and encoding it into machine-

inferrable form is the most difficult part of expert system implementation

31
AI Topics:
A Quick Introductory Overview
Machine Learning : Neural Nets

Neural nets can be used to answer the

following:

 Pattern recognition: Does that

image contain a face?

 Classification problems: Is this cell

defective?

 Prediction: Given these symptoms,

the patient has disease X

 Forecasting: predicting behavior

of stock market
 Handwriting: is character recognized?

 Optimization: Find the shortest

path for the TSP.
32
AI Topics:
A Quick Introductory Overview
Machine Learning : Neural Nets

 Artificial Neural Networks: a bottom-up attempt to model the

functionality of the brain.

 Two main areas of activity:

 Biological: Try to model biological neural systems.
 Computational:
 Artificial neural networks are biologically inspired but not necessarily
biologically plausible.
 So may use other terms: Connectionism, Parallel Distributed Processing,
Adaptive Systems Theory.

 Interests in neural networks differ according to profession.

33
AI Topics:
A Quick Introductory Overview
Nouvelle AI : Artificial Life & Complex Systems

 Artificial Life: An attempt to better understand “real” life by

in-silico modeling of the entities we are aware of.

 Motivations:
 A-Life could have been dubbed as yet-another-approach to
studying intelligent life, had it not been for the Emergent
properties in life that motivates scientists to explore the
possibility of artificially creating life and expecting the
unexpected.

 An Emergent property is created when something becomes

more than sum of its parts.

34
What is Artificial Intelligence ?
 To conclude:

 AI is a very fascinating field. It can help us solve

difficult, real-world problems, creating new
opportunities in business, engineering, and many
other application areas.

 Even though AI technology is integrated into the

fabric of everyday life. The ultimate promises of
AI are still decades away and the necessary
advances in knowledge and technology will
require a sustained fundamental research effort.

35