G51IAI Introduction to AI

Instructor: Ho Sooi Hock

Introduction

Module Introduction
Goals and Module Context
Delivery and Assessment Methods

Learning Support
Lecture Schedules AI Terminologies Applications of AI
2

Module Aims and Objectives

Define what we mean by AI (or at least give us a working definition for this module) Allow the students to become familiar with some basic AI algorithms Provide an understanding of the basic theory of a range of AI techniques and applications
3

Module Context
G51IAI Introduction to AI

G52PAS Planning and Search

G53CLP Constraint Logic Programming

G53IDS Individual Dissertation

4

Who Can Attend? (2010/2011)

G51IAI - Introduction to AI
CS First Year Compulsory CIS/CSM Second Year Option

G52PAS Planning and Search

CS Second/Third Year Option

CIS Third Year Option

Delivery & Assessments

Lectures
approx, 20 hours supplemented by self readings

2 hrs/week, Wednesday 11:00 a.m. 1:00 p.m.

Assessment
100% examination (2 hours) 4 out of 6 questions

Learning Support
Module materials online at
http://sepang.nottingham.edu.my/~hsooihock/G51IAI/
Presentations slides/notes Directed readings Past examination papers

http://www.cs.nott.ac.uk/~gxk/courses/g5aiai/

Module convenor
Room: BB71
E-mail: ho.sooi-hock@nottingham.edu.my Phone extn: 8145
7

Recommended Texts
Artificial Intelligence : A Modern Approach Third Edition by Stuart J. Russell & Peter Norvig (2010, Prentice Hall, ISBN 0-13-207148-7) (Course Text)

Artificial Intelligence : Structures and Strategies for Complex Problem Solving

Sixth Edition by George F. Luger

(2008, Addison Wesley, ISBN 0-321-54589-3)
8

Recommended Texts
Artificial Intelligence : A Modern Approach Second Edition by Stuart J. Russell & Peter Norvig (2003, Prentice Hall, ISBN 0-13-080302-2) (Course Text)

Artificial Intelligence : Structures and Strategies for Complex Problem Solving

Fifth Edition by George F. Luger

(2005, Addison Wesley, ISBN 0-321-26318-9)
9

Useful Readings
Artificial Intelligence
by Elaine Rich & Kevin Knight, McGraw-Hill

The Essence of Artificial Intelligence

by Alison Cawsey, Prentice Hall

Artificial Intelligence: a Guide to Intelligent

Systems
by Michael Negnevitsky, Addison Wesley

Fundamentals of Neural Networks: Architectures,

Algorithms and Applications
by Laurene Fausett, Prentice Hall
10

Proposed Lecture Schedule

Lecture 1 : Introduction Lecture 2 : History & Philosophy of AI Lecture 3 : Problem Formulation Lecture 4 : Blind Searches Lecture 5 : Heuristic Search Lecture 6 : Game Playing Lecture 7 : Neural Networks Lecture 8 : Neural Networks Lecture 9 : Other AI Techniques Lecture 10: Other AI Techniques Revision
11

What is AI?
A broad field that means different things to different people

Defining artificial is easy but no broad consensus in precise, concrete terms for intelligence:
exclusive province of human being? natural phenomenon exhibited by living organisms? an arbitrarily specified set of abilities?

other definitions??

12

Natural vs Machine Intelligence

Intelligence is not an unique and unshared capability of human. It is more an open collection of attributes than it is a single well-defined entity Humans embody many aspects of intelligence while animals typically embody a smaller number of intelligent characteristics, and usually at a much lower level The advent of digital computers made possible credible attempts to fulfill the AI dreams Computer based intelligence must be specialised to very restricted domains to be at all comparable to human 13 performance

Human vs Machine Intelligence

The two hemispheres of the human brain deal with problems in two distinct paradigms:
sequential (or logical) approach that considers only a small portion of the available data at a time parallel (or gestalt) processing looks at data on a global basis

Many tasks which we might reasonably think require intelligence are performed by computers without even thinking Other tasks that people do without thinking are extremely difficult to automate

Complex Arithmetic

Recognizing a Face

14

AI Problems
AI is concerned with automating both mundane and expert tasks.
Experts tasks (require specialised skills and training) include : Medical diagnosis Equipment repair Computer configuration Financial planning
15

AI Problems
Mundane tasks correspond to the following AI problems areas: Planning : The ability to decide on a good sequence of
actions to achieve our goals

Vision : Robotics:

The ability to make sense of what we see

The ability to move and act in the world, possibly responding to new perceptions The ability to communicate with others in any human language
16

Natural Language:

Mundane tasks are generally much harder to automate

AI Terminologies
Strong AI
machines can actually think intelligently

Weak AI
machine can possibly act intelligently

AIMA: Most AI researchers take the weak hypothesis for granted, and dont care about the strong AI hypothesis (Chap. 26. p. 947) Strong vs Weak AI Methods
17

Applications of AI?

Search engines Science Medicine/ Diagnosis Labor Appliances What else?

18

Contents
History and Philosophy
AI Definitions Turing Test and Chinese Room

Search Techniques
Problem Formulation State Space Search
o Tree Search: Depth-First and Breadth-First o Heuristic Search: A* Search
19

Contents
Game Playing
History Game Tree Search: mini-max and alpha-beta pruning

Neural Networks
Perceptrons Limitations Learning Algorithms

Others
TBD
20

Summary
Module goals, Structure and Contents
Course Schedule and Assessment

Practical and Administrative Matters

Review of Some Key Definitions Applications of AI

21

Directed Readings
Definitions of AI
Differentiate between
Strong and Weak AI
Strong and Weak AI Methods

22