CSE440-Artificial Intelligence

Lecture #1: Introduction

Dr. Md. Sazzad Hossain, PhD (Japan)

Professor
Department of CSE
Mawlana Bhashani Science and Technology
University

1
 Contents
Introduction of AI
History of AI
Applications of AI
Advantages and Disadvantages
Knowledge Representation System

2
 What is knowledge?

 Knowledge is a theoretical or practical

understanding of a subject or a domain.

 Knowledge is the sum of what is currently

Known.

3
 What is Intelligence?

 Someone’s intelligence is their ability to understand and

learn things.

 Intelligence is the ability to think and understand instead

of doing things by instinct or automatically.
Ø It gives some flexibility. It does not specify whether it is
someone or something that has the ability to think and
understand.

4
 What is Thinking?

 Thinking is the activity of using your brain to consider

a problem or to create an idea.
 In order to think, someone or something has to have a
brain – an organ that enables someone or something
to learn and understand things, to solve problems and
to make decisions.

5
 Intelligence?

 So we can now define Intelligence, is the ability

to learn and understand, to solve problems and
to make decisions.

6
 Intelligence Machine?

 So, a machine is thought intelligent if it can achieve

human-level performance in some situations.
 To build an intelligent machine, we have to capture,
organize and use human expert knowledge in some
problem area.

7
 What is AI?
Views of AI fall into four categories:

1 2 3 4

Thinking Acting Thinking Acting

humanly humanly rationally rationally

8
 What is AI?
(Thinking Humanly)

A given program must have some way of

1 determining how human thinks. We need to get
inside the actual working of human minds.
Thinking There are two ways to do this –
humanly: • Through introspection
The cognitive Trying to catch our own thoughts as they go by.
Modeling • Through psychological experiments
Approach
A child’s cognitive development.

9
 What is AI?
(Acting Humanly)

2 Intelligent machines must possess the

following capabilities –
Acting • Natural Language processing
humanly:
• Knowledge representation
The Turing • Automated reasoning
Test Approach • Machine learning
To pass the total Turing test, the intelligent
machine will need-
• Computer vision to perceive objects
• Robotics to manipulate objects and move
about
10
 What is AI?
(Thinking Rationally)

3  Syllogisms
Socrates is a man;
Thinking
rationally:
All men are mortal
Therefore Socrates is mortal.
The laws of  Logic
thought These laws of thought were supposed to
approach
govern the operation of mind.
Their study initiated the field called
Logic

11
 What is AI?
(Acting Rationally)

4
Rational behavior: doing the right thing
Acting
rationally: The right thing: that which is expected to
maximize goal achievement, given the
The rational
agent approach available information

12
 Brief History AI (1 of 7)
 The Dark Ages [ The birth of A.I.]: Duration: 1943-56
 Contributions: First work by Warren McCulloch & Walter
Pitts [ 1943 ]. It was on the central nervous system-a model
of neurons of the brain.
 Turing, Computing Machinery & intelligence, 1950
ENIAC (Electronic Numerical Integrator And Calculator)
by Von Neumann.
Shannon, Programming a computer for playing chess,
1950.
The Dartmouth College summer workshop on machine
intelligence, Artificial neural networks and automata
theory, 1956
 Brief History AI (2 of 7)

 Rises of A.I: Duration: 1956-late 1960s

 Contributions:
 John McCarthy (inventor of the term Artificial Intelligence)
defined the high level language LISP – one of the oldest
programming language, which is still in current use.
 General Problem Solver (GPS) by Newell & Simon, 1960
 Human Problem Solving ideas by Newell & Simon, 1972
 A framework for representing knowledge by Minsky, 1975
 Brief History AI (3 of 7)

 The Era of unfulfilled promises [ The impact of reality]

Duration: late1960s-early 1970s
 Contributions:
 The Complexity of theorem proving procedures by
Cook, 1971
 Reducibility Among Combinatorial Problems by
Karp 1972
 Brief History AI (4 of 7)
 The Discovery of expert systems
Duration: 1970s – mid 1980s
 Contributions:
 DENDRAL – the first successful knowledge-based system by
Feigenbum, Bachanan & Lederberg.
 MYCIN – another expert system by Feigenbum and Shortllife
 PROSPECTOR – an expert system for mineral exploration
developed by Stanford Research Institute
 PROLOG – A logic programming language by Colmerauer,
Roussel & Kowalski
 EMYCIN – Empty MYCIN, a domain-independent version of
MYCIN, developed by Stanford University.
 Brief History AI (5 of 7)

 The Rebirth of Artificial Neural Networks: 1965 – onward

 Contributions:
 Neural Networks & Physical Systems with Emergent
Collective Computational Abilities by Hopfield.
 Self-Organized Formation of Topological Correct
Feature maps by Kohonen
 Parallel Distributed Processing, by Rumelhart &
McClelland
 The First IEEE International Conference on Neural
Networks.
 Brief History AI (6 of 7)

 Evolutionary computation [Learning by doing]

 Duration: early 1970s – onward
 Contributions:
 Adaptation in Natural and Artificial Systems, by
Holland
 Genetic Programming: On the Programming of the
computers by means of Natural Selection by Koza
 Evolutionary computation – Towards a new philosophy
of machine intelligence by Fogel
 Brief History AI (7 of 7)
 Computing with Words: late 1980s – onwards
 Contributions:
Fuzzy sets & Algorithms by Zadeh
Application of Fuzzy logic to Approximate Reasoning
using Linguistic Synthesis by Mamdani
Expert Systems and Fuzzy Systems, by Negoita.
The First IEEE International Conference on Fuzzy
Systems
Neural Networks and Fuzzy Systems by Kosko
Fuzzy Logic, MATLAB Application Toolbox by the
MathWork, Inc.)
 Application of AI in
Medicine

 A medical clinic can use AI systems to organize bed

schedules, make a staff rotation and provide medical
information.

 AI has also application in fields of cardiology (CRG),

neurology (MRI), embryology (sonography), complex
operations of internal organs, etc.

 It also has an application in Image guided surgery and

image analysis and enhancement.
 Application of AI in
Music

 Scientists are trying to make the computer emulate the

activities of the skillful musician.

 Composition, performance, music theory, sound processing

are some of the major areas on which research in music and
AI are focusing on.
 Eg : chucks, smartmusic, etc
Application of AI in
Telecommunication

 Many telecommunications companies make use of heuristic

search in the management of their workforces.

 For example BT Group has deployed heuristic search in a

scheduling application that provides the work schedules of
20000 engineers.
 Robotics and AI

 A ROBOT is a mechanical or virtual artificial agent,

usually an electro mechanical machine that is guided by a
computer program or electronic circuitry.

 Robots can be autonomous or semi-autonomous.

 A robot may convey a sense of intelligence or thoughts of

its own.
 Application of AI in
Gaming

 In the earlier days gaming technology was not broadened.

 Physicist Willy Higinbotham created the the first video

game in 1958.

 It was called “Tennis For Tow” and was oscilloscope.

 But, now AI technology has become vast and standard has

also been increased.

 For Eg : Sudoku, Fear, Fallout, etc

 Application of AI in Banking

 Organize operations, invest in stocks, and manage

properties.

 In August 2001, robots beat humans in a simulated

financial trading competition.

 Some other applications include loan investigation, ATM

design, safe and fast banking, etc
 Some other Applications
 Credit granting
 Information management and retrieval
 AI and expert systems embedded in products
 Plant layout
 Help desk and assistance
 Employee performance evaluation
 Shipping
 Marketing
 Warehouse optimization
 In space workstation maintenance
 Satellite controls
 Network developments
 Nuclear management
Advantages and disadvantages
of AI
 Advantages :
 More powerful and more useful computers.
 New and improved interfaces.
 Solving new problems.
 Better handling of information.
 Relieves information overload.
 Conversion of information into knowledge.

 Disadvantages :
 Increased costs
 Difficulty with software development - slow and expensive
 Few experienced programmers
 Few practical products have reached the market as yet.
 Knowledge Representation System (1 of 6)

 Primary objective of A.I:

 To store knowledge so that programs can process it
and achieve the resemblance of human intelligence.
 Knowledge Representation techniques
• Rule-based
• Frame-based
• Semantic Network, etc.
Knowledge Representation system (2 of 6)
(Rule-Based)

 Features:
This is the most popular choice for building
knowledge-based systems.
Rule is the most commonly used type of
knowledge representation, which can be defined
as an IF-THEN structure.
Knowledge Representation system (3 of 6)
(Rule-Based)

Rules

IF Part THEN PART

• It is called • It is called
antecedent or consequent or
premise or conclusion or
condition. action.

An Example of this construct

So, the basic construct is- RULE #1
IF <antecedent> IF the ‘traffic light’ is
THEN <consequent> green
THEN the action is go
RULE #2
IF the ‘traffic light’ is
red
THEN the action is stop
Knowledge Representation system (4 of 6)
(Rule-Based)

 A rule can have multiple antecedents joined by the

keywords AND, OR or a combination of both.
For example,
RULE#3
IF ‘age of the customer’ < 18
AND ‘cash withdrawal’ > 1000
THEN ‘signature of the parent’ is required.
 Knowledge Representation system (5 of 6)
(Rule-Based)
Each antecedent & consequent has 3 components

Object Operator Value

RULE#3

IF ‘taxable income’ > 25000

THEN ‘Medicare levy’ = ‘taxable income’ * 1.5 / 100
Knowledge Representation system (6 of 6)
(What rules can represent?)
• Relation
IF the ‘fuel tank’ is empty
THEN the ‘car’ is dead
• Recommendation
IF the ‘season’ is autumn
AND the ‘sky’ is cloudy
THEN the ‘advice’ is ‘take an umbrella’
• Directive
IF the ‘car’ is dead
AND the ‘fuel tank’ is empty
THEN the action is ‘refuel the car’
 Knowledge Representation system
(What rules can represent?)

• Strategy
IF the ‘car’ is dead
THEN the action ‘check the fuel tank’
step 1 is complete
IF step 1 is complete
AND the ‘fuel tank’ is full
THEN the action is ‘check the battery’
step 2 is complete.
Knowledge Representation system
Basic structure of rule-based expert system

Knowledge-Base Database

Rule: IF-THEN FACT

Inference engine

Explanation Facilities

User Interface

User
 Advantages and Disadvantages of
Rule-based Knowledge Representation

Rule-base
Expert system

Advantages Disadvantage
 Natural Knowledge representation
• Opaque relations between rules
 Uniform structure
• Ineffective search strategy
 Separation of knowledge from the
• Inability to learn.
inference engine
 Dealing with incomplete and
uncertain knowledge. E.g.,
IF season is Autumn
AND sky is cloudy
AND wind is low
THEN forecast is clear {cf 0.1};
forecast is rain {cf 0.9}
 Recommended Textbooks

 [Negnevitsky, 2001] M. Negnevitsky “ Artificial Intelligence: A guide to

Intelligent Systems”, Pearson Education Limited, England, 2002.
 [Russel, 2003] S. Russell and P. Norvig Artificial Intelligence: A Modern
Approach Prentice Hall, 2003, Second Edition
 [Patterson, 1990] D. W. Patterson, “Introduction to Artificial Intelligence
and Expert Systems”, Prentice-Hall Inc., Englewood Cliffs, N.J, USA,
1990.
 [Minsky, 1974] M. Minsky “A Framework for Representing
Knowledge”, MIT-AI Laboratory Memo 306, 1974.
 [Hubel, 1995] David H. Hubel, “Eye, Brain, and Vision”
 [Ballard, 1982] D. H. Ballard and C. M. Brown, “Computer Vision”,
Prentice Hall, 1982.

37
End of Presentation

Thanks to all !!!

38