ARTIFICIAL INTELLIGENCE

LECTURE # 1: INTRODUCTION

(BSE)
1 Joddat Fatima
[email protected]

Department of Software Engineering

Bahria University Islamabad
COURSE INFORMATION

 Instructor
Mrs. JODDAT FATIMA
Cabin: NC- Ground Floor
Email: [email protected]

 Office Hours
Tuesday-Wednesday : 09:30 to 11:30

2
COURSE INFORMATION

 Course meeting times

 Lectures: 2+1 sessions/week

 Course Ressources
 S. J. Russell and P. Norvig, Artificial Intelligence: A
Modern Approach, Prentice-Hall.

 Sutton and Barto. Reinforcement Learning: An Introduction. Covers

Markov decision processes and reinforcement learning. Available
free online.
 Hastie, Tibshirani, and Friedman. The elements of statistical
learning. Covers machine learning. Available free online.
3
COURSE OBJECTIVE

Artificial Intelligence (AI) is a constantly and actively

growing and changing field. In this course, students
will learn the basics of modern AI as well as some of
the representative applications of AI.

4
COURSE CONTENTS

 Introduction to AI
 History & Application
 Intelligent Agents
 Uninformed Search
 A* Algorithm, Heuristic Search
 Adversarial Search, Game Playing
 Constraint Satisfaction Problems
 Propositional Logic
 Logical Agents
 First Order Logic
 Machine Learning
 Knowledge Representation
 Markov Decision Process I
 Game Theory 5
GRADING POLICY

6
AI?

7
 WHAT IS ARTIFICIAL INTELLIGENCE ?
 making computers that think?
 the automation of activities we associate with human
thinking, like decision making, learning ... ?
 the art of creating machines that perform functions
that require intelligence when performed by people ?
 the study of mental faculties through the use of
computational models ?

8
WHAT IS ARTIFICIAL INTELLIGENCE ?
 the study of computations that make it possible to
perceive, reason and act ?
 a field of study that seeks to explain and emulate
intelligent behaviour in terms of computational
processes ?
 a branch of computer science that is concerned with
the automation of intelligent behaviour ?
 anything in Computing Science that we don't yet
know how to do properly ? (!)

9
WHAT IS ARTIFICIAL INTELLIGENCE ?

THOUGHT Systems that thinkSystems that think

like humans rationally

Systems that act Systems that act

BEHAVIOUR like humans rationally

HUMAN RATIONAL
10
SYSTEMS THAT ACT LIKE HUMANS:
TURING TEST

 “The art of creating machines that perform

functions that require intelligence when
performed by people.” (Kurzweil)
 “The study of how to make computers do things
at which, at the moment, people are better.”
(Rich and Knight)

11
SYSTEMS THAT ACT LIKE HUMANS

 The Turing Test approach

 a human questioner cannot tell if
 there is a computer or a human answering his question, via
teletype (remote communication)
 The computer must behave intelligently
 Intelligent behavior
 to achieve human-level performance in all cognitive
tasks

12
TURING TEST

13
SYSTEMS THAT ACT LIKE HUMANS
 These cognitive tasks include:
 Natural language processing
 for communication with human
 Knowledge representation
 to store information effectively & efficiently
 Automated reasoning
 to retrieve & answer questions using the stored information
 Machine learning
 to adapt to new circumstances
 Computer vision
 to perceive objects (seeing)
 Robotics
 to move objects (acting)
14
WHAT IS ARTIFICIAL INTELLIGENCE ?

THOUGHT Systems that thinkSystems that think

like humans rationally

Systems that act Systems that act

BEHAVIOUR like humans rationally

HUMAN RATIONAL
15
SYSTEMS THAT THINK LIKE HUMANS:
COGNITIVE MODELING

 Humans as observed from ‘inside’

 How do we know how humans think?
 Introspection vs. psychological experiments
 Cognitive Science
 “The exciting new effort to make computers think …
machines with minds in the full and literal sense”
(Haugeland)
 “[The automation of] activities that we associate with human
thinking, activities such as decision-making, problem solving,
learning …” (Bellman)

16
WHAT IS ARTIFICIAL INTELLIGENCE ?

THOUGHT Systems that thinkSystems that think

like humans rationally

Systems that act Systems that act

BEHAVIOUR like humans rationally

HUMAN RATIONAL 17
SYSTEMS THAT THINK ‘RATIONALLY’
"LAWS OF THOUGHT"
 Humans are not always ‘rational’
 Rational - defined in terms of logic?
 Logic can’t express everything (e.g. uncertainty)
 Logical approach is often not feasible in terms of computation
time (needs ‘guidance’)
 “The study of mental facilities through the use of
computational models” (Charniak and McDermott)
 “The study of the computations that make it possible to
perceive, reason, and act” (Winston)

18
WHAT IS ARTIFICIAL INTELLIGENCE ?

THOUGHT Systems that thinkSystems that think

like humans rationally

Systems that act Systems that act

BEHAVIOUR like humans rationally

HUMAN RATIONAL 19
 SYSTEMS THAT ACT RATIONALLY:
“RATIONAL AGENT”

 Rational Behavior: doing the right thing

 The right thing: that which is expected to maximize goal

achievement, given the available information

 Giving answers to questions is ‘acting’.

 I don't care whether a system:

 replicates human thought processes
 makes the same decisions as humans
 uses purely logical reasoning

20
FOUNDATION OF AI

21
History

22
BRIEF HISTORY OF AI
 1923 Karel capek"s play named “Rossum's Universal
Robots” (RUR) opens in London, first use of the word
"robot" in English.
 The actual history of AI begins with the following
articles:
Turing, A.M. (1950), Computing machinery and intelligence, Mind, Vol. 59, pp. 433-460.

23
ALAN TURING - FATHER OF AI
Alan Turing (OBE, FRS)
 Born 23 June 1912, Maida Vale,
London, England
 Died 7 June 1954 (aged 41),
Wilmslow, Cheshire, England
 Fields: Mathematician, logician,
cryptanalyst, computer scientist

 Institutions:
 University of Manchester
 National Physical Laboratory
 Government Code and Cypher
School (Britain's codebreaking
centre) Alan Turing memorial statue in
 University of Cambridge Sackville Park, Manchester

24
TURING’S PAPER ON AI
 You can get this article for yourself: go to
http://www.library.manchester.ac.uk/eresources/
select ‘Electronic Journals’ and find the journal
Mind. The reference is:
 A. M. Turing, “Computing Machinery and Intelligence”,
Mind, (New Series), Vol. 59, No. 236, 1950, pp. 433-460.

You should read (and make notes on) this article as

home task. 25
BRIEF HISTORY OF AI - THE BIRTH OF AI
 1951: AI programs were developed at Manchester:
 A draughts-playing program by Christopher Strachey

 A chess-playing program by Dietrich Prinz

 These ran on the Ferranti Mark I in 1951.

 1955: Symbolic reasoning and the Logic Theorist

 Allen Newell and (future Nobel Laureate) Herbert Simon

created the "Logic Theorist". The program would

eventually prove 38 of the first 52 theorems in Russell and
Whitehead's Principia Mathematica
 1956: Dartmouth Conference – "Artificial Intelligence"
adopted

26
BRIEF HISTORY OF AI - THE BIRTH OF AI
 1956: Dartmouth Conference - "Artificial Intelligence"
adopted
 The term ‘Artificial Intelligence’ was coined in a proposal for
the conference at Dartmouth College in 1956

 The term stuck, though it is perhaps a little unfortunate . . .

27
BRIEF HISTORY OF AI
 One of the early research in AI is search problem such as
for game-playing. Game-playing can be usefully viewed as
a search problem in a space defined by a fixed set of rules

 Nodes are either white or black corresponding to reflect

the adversaries’ turns.
 The tree of possible moves can be searched for favourable 28
positions.
BRIEF HISTORY OF AI

 Another of the early research in AI was applied the

similar idea to deductive logic:

All men are mortal x ( man(x) -> mortal(x) )
Socrates is a man man(Socrates)
Socrates is mortal mortal(Socrates)

 The discipline of developing programs to perform such

logical inferences is known as (automated) theorem-
proving

29
BRIEF HISTORY OF AI - GOLDEN YEARS 1956-74
 Research:
 Reasoning as search: Newell and Simon developed a
program called the "General Problem Solver".
 Natural language Processing: Ross Quillian proposed the
semantic networks and Margaret Masterman & colleagues at
Cambridge design semantic networks for machine translation
 Lisp: John McCarthy (MIT) invented the Lisp language.
 Funding for AI research:
 Significant funding from both USA and UK governments
 The optimism:
 1965, Simon: "machines will be capable, within twenty years,
of doing any work a man can do
 1970, Minsky: "In from three to eight years we will have a
machine with the general intelligence of an average human
being." 30
BRIEF HISTORY OF AI - THE FIRST AI WINTER
1974−1980:
 Problems
 Limited computer power: There was not enough memory or
processing speed to accomplish anything truly useful
 Intractability and the combinatorial explosion. In 1972
Richard Karp showed there are many problems that can
probably only be solved in exponential time (in the size of the
inputs).
 Common-sense knowledge and reasoning. Many
important applications like vision or natural language require
simply enormous amounts of information about the world and
handling uncertainty.
 Critiques from across campus
 Several philosophers had strong objections to the claims being
made by AI researchers and the promised results failed to
materialize
 The end of funding
 The agencies which funded AI research became frustrated 31
with the lack of progress and eventually cut off most funding
for AI research.
BRIEF HISTORY OF AI - BOOM 1980–1987
1980–1987:
 In the 1980s a form of AI program called "expert systems"
was adopted by corporations around the world and
knowledge representation became the focus of mainstream
AI research
 The power of expert systems came from the expert knowledge
using rules that are derived from the domain experts
 In 1980, an expert system called XCON was completed for the
Digital Equipment Corporation. It was an enormous success: it
was saving the company 40 million dollars annually by 1986
 By 1985 the market for AI had reached over a billion dollars

 The money returns: the fifth generation project

 Japan aggressively funded AI within its fifth generation
computer project (but based on another AI programming
language - Prolog created by Colmerauer in 1972)
32
 This inspired the U.S and UK governments to restore funding

for AI research
BRIEF HISTORY OF AI
 The real success of AI in game-playing was achieved much
later after many years’ effort.
 It has been shown that this search based approach works
extremely well.
 In 1996 IBM Deep Blue beat Gary Kasparov for the first
time. and in 1997 an upgraded version won an entire match
against the same opponent.

33
BRIEF HISTORY OF AI - AI 1997−PRESENT
 1997 The Deep Blue Chess Program beats the then world chess
champion, Garry Kasparov.

 2000 Interactive robot pets become commercially available. MIT

displays Kismet, a robot with a face that expresses emotions. The
robot Nomad explores remote regions of Antarctica and locates
meteorites

 Significant progress has been achieved in neural networks,

probabilistic methods for uncertain reasoning and statistical
machine learning, machine perception (computer vision and
Speech), optimisation and evolutionary computation, fuzzy
systems, Intelligent agents.

34
AI Application

35
AI SUB-DOMAINS

36
AI APPLICATIONS
 Autonomous
Planning &
Scheduling:
 Autonomous rovers.

37
AI APPLICATIONS
 Autonomous Planning & Scheduling:
 Telescope scheduling

38
AI APPLICATIONS
 Autonomous Planning & Scheduling:
 Analysis of data:

39
AI APPLICATIONS

40
AI APPLICATIONS
 Medicine:
 Image guided surgery

41
AI APPLICATIONS

42
AI APPLICATIONS
 Medicine:
 Image analysis and enhancement

43
AI APPLICATIONS
 Transportation:
 Autonomous vehicle
control:

44
AI APPLICATIONS
 Human detection:

45
AI APPLICATIONS

46
AI APPLICATIONS

47
AI APPLICATIONS

Games:

48
AI APPLICATIONS
 Games:

49
AI APPLICATIONS
 Robotic toys:

50