|
|
|
|
|
Course Overview |
|
What is AI ? |
|
A brief History |
|
The state of the art |
|
|
|
|
|
|
An understanding of: |
|
what AI is, |
|
what methodologies are considered AI, |
|
what can AI methodologies accomplish and, |
|
what are the limitations of AI |
|
Students will be able to: |
|
implement various AI methodologies, |
|
understand and write programs in the programming
languages, Prolog and LISP |
|
build a moderately sized AI-based program. |
|
|
|
|
|
|
|
|
Introduction (chaps 1&2). |
|
Search (chaps 3, 4) |
|
Games playing (chap 5) |
|
Logic and inference (chaps 6, 7, 9, 10) |
|
Learning. (chaps 18, 19, 21). |
|
Planning. (chap 11) |
|
|
|
There are two exams: a midterm exam and a final
exam. |
|
There will be 6 homework assignments. |
|
There is a final project. Each student will work
individually on an implementation of some system that employs an artificial
intelligence methodology. Although we will examine the Prolog and LISP in
this class, it is not necessary for this final project to be written in
either of these languages. |
|
|
|
|
|
|
|
|
Midterm Exam 20% |
|
Final Exam
20% |
|
Homework 30% |
|
Final Project 25% |
|
Class Participation 5% |
|
|
|
|
|
|
|
|
Intelligent Agents |
|
Solving Problems by Searching |
|
Informed Search Methods |
|
Game Playing |
|
Logical Systems |
|
Learning |
|
Planning Systems |
|
|
|
|
|
|
Alan Turing in 1950 designed this test to
provide a satisfactory operational definition of intelligence. |
|
Imitation Game: |
|
|
|
|
Predicted that by 2000, a machine might have a
30% chance of fooling a lay person for 5 minutes |
|
Anticipated all major arguments against AI in
following 50 years |
|
Suggested major components of AI: knowledge,
reasoning, language, understanding, learning |
|
Problem: Turing test is not reproducible,
constructive, or amenable to mathematical analysis |
|
|
|
|
|
|
Natural language processing |
|
knowledge representation |
|
automated reasoning |
|
machine learning |
|
computer vision |
|
robotics |
|
|
|
|
|
|
1960s “cognitive revolution”:
information-processing psychology replaced prevailing orthodoxy of
behaviorism |
|
Requires scientific theories of internal
activities of the brain |
|
What level of abstraction? “knowledge” or
“circuits” |
|
How to validate? Requires: |
|
Predicting and testing behavior of human
subjects (top-down) |
|
Direct identification from neurological date
(bottom-up) |
|
Both approaches (roughly, Cognitive Science and
Cognitive Neuroscience) are now distinct from AI |
|
|
|
