G51IAI Introduction

download G51IAI Introduction

of 22

Transcript of G51IAI Introduction

  • 7/30/2019 G51IAI Introduction

    1/22

    1

    G51IAI

    Introduction to AI

    Instructor: Ho Sooi Hock

    Introduction

  • 7/30/2019 G51IAI Introduction

    2/22

    2

    Module Introduction

    Goals and Module Context

    Delivery and Assessment Methods

    Learning Support

    Lecture Schedules

    AI Terminologies

    Applications of AI

  • 7/30/2019 G51IAI Introduction

    3/22

    3

    Module Aims and Objectives

    Define what we mean by AI (or at leastgive us a working definition for thismodule)

    Allow the students to become familiarwith some basic AI algorithms

    Provide an understanding of the basictheory of a range of AI techniques andapplications

  • 7/30/2019 G51IAI Introduction

    4/22

    4

    Module Context

    G51IAI

    Introduction to AI

    G52PAS

    Planning and Search

    G53CLP Constraint

    Logic Programming

    G53IDS Individual Dissertation

  • 7/30/2019 G51IAI Introduction

    5/22

    5

    Who Can Attend? (2010/2011)

    G51IAI - Introduction to AI

    CS First Year Compulsory

    CIS/CSM Second Year Option

    G52PASPlanning and Search

    CS Second/Third Year Option

    CIS Third Year Option

  • 7/30/2019 G51IAI Introduction

    6/22

    6

    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 6questions

  • 7/30/2019 G51IAI Introduction

    7/22

  • 7/30/2019 G51IAI Introduction

    8/22

    8

    Recommended TextsArtificial 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)

  • 7/30/2019 G51IAI Introduction

    9/22

    9

    Recommended TextsArtificial 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)

  • 7/30/2019 G51IAI Introduction

    10/22

    10

    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 IntelligentSystems

    by Michael Negnevitsky, Addison Wesley

    Fundamentals of Neural Networks: Architectures,Algorithms and Applications

    by Laurene Fausett, Prentice Hall

  • 7/30/2019 G51IAI Introduction

    11/22

    11

    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

  • 7/30/2019 G51IAI Introduction

    12/22

    12

    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??

  • 7/30/2019 G51IAI Introduction

    13/22

    13

    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 whileanimals 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

    performance

  • 7/30/2019 G51IAI Introduction

    14/22

    14

    Human vs Machine Intelligence

    Many tasks which we might

    reasonably think requireintelligence

    are performed by computers withouteven thinking

    Complex

    Arithmetic

    Other tasks that people do without

    thinking are extremely difficult to

    automate

    Recognizing

    a Face

    The two hemispheres of the human brain deal with problems intwo distinct paradigms:

    sequential (or logical) approach that considers only a small

    portion of the available data at a time

    parallel (or gestalt) processinglooks at data on a global basis

  • 7/30/2019 G51IAI Introduction

    15/22

    15

    AI Problems

    Experts tasks (require specialised skills and training) include :

    Medical diagnosis

    Equipment repair

    Computer configuration

    Financial planning

    AI is concerned with automating both mundane

    and expert tasks.

  • 7/30/2019 G51IAI Introduction

    16/22

    16

    AI Problems

    Mundane tasks correspond to the following AI problems areas:

    Planning :

    Vision :

    Robotics:

    Natural Language:

    The ability to decide on a good sequence of

    actions to achieve our goals

    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

    Mundane tasks are generally much harder to

    automate

  • 7/30/2019 G51IAI Introduction

    17/22

    17

    AI Terminologies

    Strong AI machines can actually think intelligently

    Weak AI machine can possibly act intelligently

    AIMA: Most AI researchers take the weakhypothesis for granted, and dont care about the

    strong AI hypothesis(Chap. 26. p. 947)

    Strong vs Weak AI Methods

  • 7/30/2019 G51IAI Introduction

    18/22

    18

    Applications of AI?

    Search engines

    Labor

    Science

    Medicine/Diagnosis

    AppliancesWhat else?

  • 7/30/2019 G51IAI Introduction

    19/22

    19

    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

  • 7/30/2019 G51IAI Introduction

    20/22

    20

    Contents

    Game Playing

    History

    Game Tree Search: mini-max and alpha-beta pruning

    Neural Networks

    Perceptrons

    Limitations

    Learning Algorithms

    Others

    TBD

  • 7/30/2019 G51IAI Introduction

    21/22

    21

    Summary

    Module goals, Structure and Contents

    Course Schedule and Assessment

    Practical and Administrative Matters

    Review of Some Key Definitions

    Applications of AI

  • 7/30/2019 G51IAI Introduction

    22/22

    22

    Directed Readings

    Definitions of AI

    Differentiate between

    Strong and Weak AI

    Strong and Weak AI Methods