CS289 - Department of Computing

Download Report

Transcript CS289 - Department of Computing

Introduction to AI
Module – CS289
Introduction to
Artificial Intelligence – CS289
04th September 2006
Dr Bogdan L. Vrusias
[email protected]
Introduction to AI
Module – CS289
Fundamental Questions of AI
(Alan Turing asked:)
Is there thought without experience?
Is there mind without communication?
Is there language without living?
Is there intelligence without life?
…
Can machines think?
4th September 2006
Bogdan L. Vrusias © 2006
2
Introduction to AI
Module – CS289
CS289 Aims
• The aim of this module is:
– This module aims to demonstrate a variety of techniques for
capturing human knowledge and represent it in a computer, in a
way that enables the machine to reason over the data represented,
and mimic the human ability to deal with incomplete or uncertain
data.
4th September 2006
Bogdan L. Vrusias © 2006
3
Introduction to AI
Module – CS289
CS289 Outcomes
• At the end of the module students should be able to:
– Describe methods for acquiring human knowledge.
– Evaluate which of the acquisition methods would be most
appropriate in a given situation.
– Describe techniques for representing acquired knowledge in a way
that facilitates automated reasoning over the knowledge.
– Categorise and evaluate AI techniques according to different
criteria such as applicability and ease of use, and intelligently
participate in the selection of the appropriate techniques and tools,
to solve simple problems.
– Use the presented techniques in practice to develop an “intelligent”
system.
4th September 2006
Bogdan L. Vrusias © 2006
4
Introduction to AI
Module – CS289
CS289 Content I
• Knowledge-Based Intelligent Systems
– Artificial intelligence from the ‘Dark Ages’ to knowledge-based
systems
– What is knowledge?
– Knowledge representation techniques
– Rules as a knowledge representation technique and Expert Systems
4th September 2006
Bogdan L. Vrusias © 2006
5
Introduction to AI
Module – CS289
CS289 Content II
• Uncertainty Management in Expert Systems
– Introduction to uncertainty
– Bayesian reasoning
– Certainty factors theory and evidential reasoning
4th September 2006
Bogdan L. Vrusias © 2006
6
Introduction to AI
Module – CS289
CS289 Content III
• Fuzzy Expert Systems
– Fuzzy sets and linguistic variables and hedges
– Fuzzy inference for building a fuzzy expert system
4th September 2006
Bogdan L. Vrusias © 2006
7
Introduction to AI
Module – CS289
CS289 Content IV
• Machine Learning
–
–
–
–
Introduction to learning
Decision Trees
Introduction to Artificial Neural Networks
Introduction to Evolutionary Computation
4th September 2006
Bogdan L. Vrusias © 2006
8
Introduction to AI
Module – CS289
CS289 Content V
• Knowledge Engineering and Data Mining
– Introduction to knowledge engineering
– How to find the tools that will work for my problem
– Data mining and knowledge discover
4th September 2006
Bogdan L. Vrusias © 2006
9
Introduction to AI
Module – CS289
Assessment Pattern
Unit(s) of Assessment
Weighting Towards
Module Mark (%)
Coursework
25
Verbal Examination (based on the coursework)
15
Examination
60
Qualifying Condition(s)
A weighted aggregate mark of 40% is required to pass the module.
4th September 2006
Bogdan L. Vrusias © 2006
10
Introduction to AI
Module – CS289
Coursework
• The students are expected to participate in a group project
focused on studying the architecture and behaviour of an
fuzzy logic system.
• Students may use a pre-existing program (shell) or write
their own.
– The department will provide the Matlab Fuzzy Logic tool,
– but, there are web sites which contain AI freeware and the students
are expected to make the most of this freeware.
• The student is expected to write an individual 10-page
(max) report on his or her study, not exceeding 3000
words.
– More details will be give at appropriate time.
4th September 2006
Bogdan L. Vrusias © 2006
11
Introduction to AI
Module – CS289
Methods of Teaching/Learning
• The module will consist of 24 hours of lectures, and 6
practical tutorial hours.
• NOTE: Attending lectures is VERY important!
4th September 2006
Bogdan L. Vrusias © 2006
12
Introduction to AI
Module – CS289
On-line Resources
• CS289 main resource
– http://www.cs.surrey.ac.uk/teaching/cs289
NOTE: Make sure you check the module website regularly!
• The WWWW (i.e http://www.google.com !!!)
4th September 2006
Bogdan L. Vrusias © 2006
13
Introduction to AI
Module – CS289
Selected Texts
• The main course book for this module that contains most
of the theoretical material is:
– Negnevitsky, Michael (2004), Artificial Intelligence – A Guide to
Intelligent Systems (Second Edition), Harlow, UK, Addison
Wesley, ISBN: 0321204662.
4th September 2006
Bogdan L. Vrusias © 2006
14
Introduction to AI
Module – CS289
Selected Texts II
• Other recommended books are:
– Luger, G.F (2004) Artificial Intelligence: Structures &
Strategies for Complex Problem Solving (Fifth Edition).
London: Addison-Wesley, ISBN: 0321263189.
– Callan, Rob (2003), Artificial Intelligence, Basingstoke,
Hampshire, UK, Palgrave MacMillan, ISBN: 0333801369.
– Winston, Patrick H. (1992), Artificial Intelligence (Third
Edition), Reading (MASS): Addison-Wesley Publishers
Co, ISBN: 0201533774.
4th September 2006
Bogdan L. Vrusias © 2006
15
Introduction to AI
Module – CS289
Learning contract – for us all
•
•
•
•
Punctuality
No disruption of other’s learning
Mobile phones!
Availability (office 06BB02):
– Tuesdays 14:00 - 16:00
• Communication: email and the student hours
• Fun
4th September 2006
Bogdan L. Vrusias © 2006
16
Introduction to AI
Module – CS289
Discussion
• Can machines think?
• Can machines see?
• How does a human mind work? Is it magic?
• Can non-humans have minds?
• Can machines replace a human worker?
• Are intelligent machines good or bad for humans?
• Would you trust one?
4th September 2006
Bogdan L. Vrusias © 2006
17
Introduction to AI
Module – CS289
What is Intelligence?
• Intelligence is the ability to understand and learn things.
• Intelligence is the ability to think and understand instead
of doing things by instinct or automatically.
• (Essential English Dictionary, Collins, London, 1990).
• Intelligence is the ability to learn and understand, to solve
problems and to make decisions.
4th September 2006
Bogdan L. Vrusias © 2006
18
Introduction to AI
Module – CS289
What is Artificial Intelligence?
• The goal of artificial intelligence (AI) as a science is to
make machines do things that would require intelligence if
done by humans.
• AI is a branch of computing science that deals with the
specification, design and implementation of information
systems that have some knowledge related to the
enterprise in which the information systems are situated.
• Such systems are designed per se to be responsive to the
needs of their end-users.
4th September 2006
Bogdan L. Vrusias © 2006
19
Introduction to AI
Module – CS289
Turing Imitation Game
• The British mathematician Alan Turing, over fifty years
ago, inventing a game, the Turing Imitation Game.
• The imitation game originally included two phases:
4th September 2006
Bogdan L. Vrusias © 2006
20
Introduction to AI
Module – CS289
Turing Imitation Game – Phase 1
In the first phase, the interrogator, a man
and a woman are each placed in separate
rooms. The interrogator’s objective is to
work out who is the man and who is the
woman by questioning them. The man
should attempt to deceive the interrogator
that he is the woman, while the woman
has to convince the interrogator that she is
the woman.
4th September 2006
Bogdan L. Vrusias © 2006
21
Introduction to AI
Module – CS289
Turing Imitation Game – Phase 2
In the second phase of the game, the man
is replaced by a computer programmed to
deceive the interrogator as the man did. It
would even be programmed to make
mistakes and provide fuzzy answers in the
way a human would. If the computer can
fool the interrogator as often as the man
did, we may say this computer has passed
the intelligent behaviour test.
4th September 2006
Bogdan L. Vrusias © 2006
Second Phase
22
Introduction to AI
Module – CS289
Turing Remarks
• By maintaining communication between the human and
the machine via terminals, the test gives us an objective
standard view on intelligence.
• A program thought intelligent in some narrow area of
expertise is evaluated by comparing its performance with
the performance of a human expert.
• To build an intelligent computer system, we have to
capture, organise and use human expert knowledge in
some narrow area of expertise.
4th September 2006
Bogdan L. Vrusias © 2006
23
Introduction to AI
Module – CS289
Some AI Examples
• Please check the following websites on your free time:
–
–
–
–
–
–
–
–
http://www.generation5.org/jdk/demos.asp
http://www.aridolan.com/ofiles/eFloys.html
http://www.aridolan.com/ofiles/iFloys.html
http://www.arch.usyd.edu.au/~rob/#applets
http://www.softrise.co.uk/srl/old/caworld.html
http://people.clarkson.edu/~esazonov/neural_fuzzy/loadsway/LoadSway.htm
http://www.iit.nrc.ca/IR_public/fuzzy/FuzzyTruck.html
http://www.pandorabots.com/pandora/talk?botid=f5d922d97e345aa1
4th September 2006
Bogdan L. Vrusias © 2006
24
Introduction to AI
Module – CS289
Closing
•
•
•
•
Questions???
Remarks???
Comments!!!
Evaluation!
4th September 2006
Bogdan L. Vrusias © 2006
25