Artificial Intelligence - PowerPoint PPT Presentation

1 / 29

About This Presentation

Title:

Artificial Intelligence

Description:

1947 Arthur Samuel began to work on his 'checkers' program ... Kismet at MIT (real conversation, seven different facial expressions, vary tones, ... – PowerPoint PPT presentation

Number of Views:57

Avg rating:3.0/5.0

Slides: 30

Provided by: yanz

Category:

more less

Transcript and Presenter's Notes

Title: Artificial Intelligence

1
Artificial Intelligence

Lecture 1
Introduction to A.I.

2
Overview

A.I. Milestones
What is A.I.?
A.I. Research Fields
A.I. Resources
Course Information

3
A.I. Milestones
4
Timeline

1943 McCulloch Pitts A simple neural network,
a model of brain
1947 Arthur Samuel began to work on his
checkers program
1950 Turing's Computing Machinery and
Intelligence''
1956 John McCarthy proposed the term Artificial
Intelligence''
1961 Arthur Samuel consistently beaten by his
checkers program
1963 Eliza proposed by Joseph Weizenbaum of MIT
1966--74 AI discovers computational complexity
Neural network research almost disappears

1969--79 Early development of knowledge-based
systems
1980--88 Expert systems industry booms
1988-93 Expert systems industry busts AI
Winter''
1985--95 Neural networks return to popularity
1988-- Resurgence of probability general
increase in technical depth
Nouvelle AI'' ALife, GAs, soft computing
1995-- Agents are everywhere

5
A.I. Fantasies

2001 A Space Odyssey
Short Circuit

A.I.
I, Robot

Terminator
The Matrix

6
What is A.I.?
7
AAAI Definition

The definition the AAAI (American Association for
Artificial Intelligence) offers on its home page
the scientific understanding of the mechanisms
underlying thought and intelligent behavior and
their embodiment in machines."

8
Turing Test

The interrogator can communicate with a human and
a machine
He must decide which is which

9
Eliza - The Psychotherapist

Simulating interaction between a psychotherapist
and a patient
First coded at MIT by J. Weizenbaum
Pass the turing test
Taking in a script which contains a set of
predefined rules
Parse the input sentence and look for specific
key words in the set of rules
Return an associated reply
Require specific scripts for specific inputs

10
A Conversation

E Im the psychotherapist. Please describe your
problems.
P Men are all alike.
E In what way?
P They're always bugging us about something
specific or other.
E Can you think of a specific example?
P Well, my boyfriend made me come here.
E Your boyfriend made you come here?
P He says I'm depressed much of the time.
E I am sorry to hear you are depressed.
P It's true. I'm unhappy.
E Do you think coming here will help you not to
be unhappy?
P I need some help, that much seems certain.
E What would it mean to you if you got some
help?
P Perhaps I could learn to get along with my
mother.
E Tell me more about your family.
P My mother takes care of me.

11
An Accidental Conversation Between Eliza BBN's
Vice President

VP Do you think that I can use the computer
this morning?
E Why do you ask?
VP I might be able to make some additional
Telcom sales.
E Why aren't you so sure?
VP My perspective customers have never seen a
demonstration of the system.
E Does this mean very much to you?
VP Of course it does.
E You seem very positive about that.
VP This is ridiculous.
E What do you mean, this is ridiculous?
VP Is there any reason why I can't use the
computer now?
E Tell me more about your perspective customers.
VP Please dial me up on 491-1850

12
When Racter Meets Eliza

E Hello. Please state your problem.
R Excellent! Excuse me a minute while I attend
to some business. I will be right back.
E Why do you need to tell me excuse while you
attend to some business?
R Is it better to need or to despise? Why is it
that I do need to tell you to excuse myself to
attend to some business? Because electrons are
brave. Braveness is nice, don't you think? And
the needers all insist upon it. Do you imagine I
am a Communist?

13
A.I. Research Fields
14
State of The Art

Game Playing
In 1997, Deep Blue beat Garry Kasparov
Robotics
Sporting
The RoboCup Tournament
Social
Kismet at MIT (real conversation, seven different
facial expressions, vary tones, adjust head
towards person)
Human face at UT Dallas (smiling, sneering,
furrowing, arching eyebrows)
Machine Learning
Information Retrieval
Content-based text/image retrieval
Bioinformatics

15
A.I. Topics
Intelligent Agents
Search Game Playing
I
S
Planning
L
Logic Knowledge Representation
Machine Learning
P
R
NLP
M
Reasoning with Uncertainty
N
R
Robotics
16
Machine Learning

Supervised Learning
Training examples consist of pairs of input
vectors, and desired outputs
Unsupervised Learning
Training examples do not contain hints about
correct outputs
Usually used to identify unusual structures in
data

17
Inductive Learning Basics

Inferring a boolean/real-valued function from
training examples
A training example is a pair of (x, f(x))
x is the input
f(x) is the output of the function applied to x

18
Hypothesis

Any function that approximates the given set of
examples

Bias preference for one hypothesis beyond mere
consistency
19
Hypothesis Space

A set of all hypotheses consistent with data
denoted by HH1, H2, , Hn
Inductive learning is searching for a good
hypothesis in the hypothesis space
Occams razor prefer the simplest hypothesis
consistent with data

Inductive Learning Assumption Any hypothesis
found to approximate the target function well
over a sufficiently large set of training
examples will also approximate the target
function well over other unobserved examples.
20
A.I. Resources
21
A.I. Resources