Transcript roass-2004 - Department of Computer Science

74.419 Artificial Intelligence
Course Introduction and ROASS Document
Course Info
Course Topics and approximate Schedule
Assignments and Grade Breakdown
The usual Stuff (including ‘How to fail this course’)
Students introduce themselves
74.419 Artificial Intelligence
- Course Info Time:
Mon, Wed, Fri 2:30-3:20 pm
Prerequisites:
74.319 Introduction to Artificial
Intelligence
Web page:
http://www.cs.umanitoba.ca/~cs419
News Group:
local.cs419
Instructor:
Dr. Christel Kemke
Textbook:
Russell/Norvig: Artificial Intelligence
Instructor Info
Dr. Christel Kemke
562 Machray Hall
Phone: (204) 474-8674
e-Mail:
[email protected]
Office Hours: Tuesday 1:00-3:00pm
Mon, Wed after class
by appointment
Main Textbook
Stuart Russell and Peter Norvig, Artificial
Intelligence – A Modern Approach, Prentice
Hall, 1995 & 2003
available in The Bookstore, ~ 95 CAD
Course Objectives
Essential and Advanced Knowledge and Skills
in Artificial Intelligence
Learning
basic and advanced knowledge
Experience
through tasks and projects
Skills
scientific, research and applied
Preparation
for work and advanced studies
(You will get a bit of LISP, too.)
Class Structure
Classes will comprise of
• Lectures with Notes
• Online Videos, Movies (PBS, SRI)
• Student Project Presentations (one-day
‘conference’)
• Occasional in-class Exercises
Topics Outline
 The Dream – Flakey and other Agents
– SRI Movie
– General Introduction to Agents
 Knowledge Representation & Reasoning
–
–
–
–
–
–
–
Review Propositional Calculus
First-Order Predicate Logic including Semantics !
Representation with Frames, Inheritance Hierarchies, ...
A tiny bit of Description Logics
Ontology - where elephant sometimes have 3 legs
Allen’s Time Logic
Exotic Logics (like Deontic Logic) - who likes Hawaii and can
we go there or do we have to go there or can we not go there?
Topics Outline 2
 Planning
–
–
–
–
–
–
–
–
Introduction with Shakey - The first "Real Robot"
Planning as Search – STRIPS
ABSTRIPS
Partial-Order Planning
Hierarchical Plan Decomposition
Situation Calculus
Standard Problems (everywhere in this section)
Special Topics (?) or maybe more videos?
Topics Outline 3
 Natural Language Processing
– a short Introduction to Speech Recognition (nothing
but 'hot air')
– Overview of Natural Language Processing (NLP)
– Syntax, Grammar - "What's up" could really be a
real sentence, and find this out here:
– Syntactic Sentence Analysis, or Parsing
(Chartparser, Earley-Algorithm)
– a little bit of Semantics (What does that mean?)
– something about Discourse and Dialogue ("I will get
a cold!" or "Could you please close the door?")
– Command Talk video and some demos
Topics Outline 4 – ‘Free Style’
(optional part)
Neural Networks
–
–
–
–
General NN Model & Processing
NN Architectures
Learning Paradigms for Neural Networks
some example demos, maybe a video
Evolutionary Algorithms
– General Principles of Evolutionary Computing
– more videos (than theory)
Main Textbook
Stuart Russell and Peter Norvig, Artificial
Intelligence – A Modern Approach, Prentice
Hall, 1995 & 2003
available in The Bookstore, ~ 95 CAD
Russell and Norvig Textbook:
Table of Contents
I. ARTIFICIAL INTELLIGENCE.
1. Introduction.
2. Intelligent Agents.
II. PROBLEM-SOLVING.
3. Solving Problems by Searching.
4. Informed Search and Exploration.
5. Constraint Satisfaction Problems.
6. Adversarial Search.
III. KNOWLEDGE AND REASONING.
7. Logical Agents.
8. First-Order Logic.
9. Inference in First-Order Logic.
10. Knowledge Representation.
IV. PLANNING.
11. Planning.
12. Planning and Acting in the Real World.
V. UNCERTAIN KNOWLEDGE AND
REASONING.
13. Uncertainty.
14. Probabilistic Reasoning Systems.
15. Probabilistic Reasoning Over Time.
16. Making Simple Decisions.
17. Making Complex Decisions.
VI. LEARNING.
18. Learning from Observations.
19. Knowledge in Learning.
20. Statistical Learning Methods.
21. Reinforcement Learning.
VII. COMMUNICATING, PERCEIVING,
AND ACTING.
22. Communication.
23. Probabilistic Language Processing.
24. Perception.
25. Robotics.
VIII. CONCLUSIONS.
26. Philosophical Foundations.
27. AI: Present and Future.
Second AI Textbook
Nils J. Nilsson, Artificial Intelligence – A
New Synthesis, Morgan Kaufman, 1998
Another AI Textbook
George Luger and William Stubblefield:
Artificial Intelligence, Addison-Wesley, 1998
and 2001 (CS 319 textbook)
Reference Book - NLP
Daniel Jurafsky / James Martin, Speech and
Language Processing, Prentice Hall, 2000
Reference Book - KR and Logic
Richard A. Frost, Introduction to KnowledgeBase Systems, Collins, 1986
too old to be shown.
Assignments
3 Homework Assignments
• Knowledge Representation
• Planning
• Natural Language Processing
Group Project (3 Students)
Design and Implementation of an Intelligent Agent
System with Knowledge Base, Planning Module,
and simple Natural Language Interface, modeling
– a Household Robot or
– a Mars Rover or
– your own Agent (if confirmed by the instructor)
Grade Breakdown
Project
Homework (all 3 together)
Final Exam
20%
30%
50%
100%
In addition, you can get Bonus Points for exceptional
efforts, good in-class participation, work beyond
requirements. These can be a few percent, which are
calculated on top of the 100% scale.
Course Schedule (approximately)
Introduction
Knowledge Represent.
Planning
Lab
Natural Language Proc.
Free Style
week 1
8-12 Sept
week 2-5
week 6-7
week 8
27-31 Oct
week 9-10
week 11
Group Project Present.
week 12
Exam preparation
last week
3-5 Dec
Deadline Policy
Assignments are to be submitted before the due date.
Unless otherwise specified, they have to be dropped
into the slot for CS 419 outside the Cargill Lab.
Electronic submissions (program code) has to be sent
to [email protected] (except final project).
Extensions to a deadline can be granted only by the
instructor (Dr. Kemke). In general, no late
assignment will be accepted after the marked
assignments have been returned.
KEEP COPIES OF SUBMITTED ASSIGNMENTS!
Class Communication, Notes,
Attendance
• Class Notes will in general be provided via
the course web page
• Non-web material will be made accessible
on-line or in a Course Folder in the Library
• Class attendance is not checked but students
are responsible for knowing the contents of
the classes
• Course news group will be set up
• Questions can be sent via e-mail to me
How to Fail this Course or
Get a Bad Grade
• A good starting point is not to attend classes on a
regular basis.
• Do not look at the Course Notes either. Just forget
about the whole course web site.
• Never ever ask or talk to fellow students or the
instructor about the course contents. If you missed a
class (or more) or if you can't grasp something, just
hide it and play cool.
How to Fail this Course or
Get a Bad Grade
• Don't cooperate with your project partners in the
group project. Tell them you have so many other
things to do, you just don't have the time to meet and
work with them.
• Do not come to the presentation of your group
project. Or ask the instructor for a last minute change
of the schedule (The best time is the morning of the
day when your presentation is scheduled.)
How to Fail this Course or
Get a Bad Grade
• Do not attend the exam preparation.
• The safest way to fail the course is:
Go on holidays during exam time, or hide in a safe
place. Wait there until exam time is over. After
Christmas, get in touch with the Faculty/ Department/
Instructor and ask for special permission to take the
exam now.
Course Partner
Every student is asked to have a course partner!
Course Partners have a mutual commitment to
inform each other about the class contents, in
case one of them has missed a class (for
acceptable reasons).
In case both course partners have to miss a class,
they are asked to contact other students, and if
necessary the instructor, to inform themselves
on the class contents.
Illness and other problems
In case of longer times of illness or other
problems like bereavement, which
considerably influence class attendance and
course performance, students are advised to
contact the instructor in order to find
arrangements for continuing successfully with
the course.
In case students encounter other substantial
course-related problems, they are also advised
to contact the instructor or TA.
Misuse of Computer Facilities,
Plagiarism, and Cheating
• These serious offenses will carry sanctions.
Copying of assignments or parts thereof from
anywhere without appropriate references, cheating
on exams, or misusing facilities will result in
punishment ranging from course failure to
prosecution.
• Please see section 7 of the General Academic
Regulations and Requirements in the U of M
General Calendar for more information.
Final Exam
• Time and location of the final exam will be
announced by the Student Records Office. It is
your own responsibility to make yourself aware of
the posted exam schedules. You are obligated to
make yourself available for the writing of the final
exam.
• Advice for preparing the final exam will be given
at an appropriate time in class.