CPS 481/581:  Advanced Artificial Intelligence

Spring Semester 2011       3 credits

Meets:  T  Th   4:30-5:45pm

203 Miriam Hall

 

Professor:  Dr. Jennifer Seitzer                      

Office: 144 Anderson Hall

Email:  seitzer@udayton.edu

Course Web Page:            http://homepages.udayton.edu/~jseitzer1/cps480

Phone: (937) 229-2197

*Office Hours:  

  • Wed:     11-2pm
  • Thur:     3-4pm
  • By appointment

Mailing Address:

Dr. Jennifer Seitzer, Associate Professor

Computer Science Department

University of Dayton

300 College Park

Dayton, OH 45469-2160

 

Prerequisites:

CPS 480:  Artificial Intelligence.

 

Motivation:

Artificial Intelligence is the sub-discipline of computer science that attempts to endow intelligence to computer systems.    Although AI has produced some very sophisticated computer systems, it is generally accepted that the goal of systems achieving human-level intelligence is still elusive.

 

There are two general approaches to the pursuit of artificial intelligence.  The symbolic is often referred to as "good old fashioned AI" (philosopher John Haugeland) and is abbreviated as:  GOFAI.  This is based on the belief that thinking can be accomplished by a physical symbol system -- that the manipulation of a physical symbol system provides necessary and sufficient means for intelligent behavior [Newell and Simon 1976].   The subsymbolic approach to AI employs techniques that mimic organisms in nature including the human neuron as well collective and individual insect behavior.  In fact, part of this camp of researchers believe that thinking can only occur in machines made of proteins [Searle 1980, 1992]. 

 

In this course, we will address some traditional areas of AI including default reasoning, fuzzy logic, planning, and machine learning.  We will also broach a few topics spawned from the sub-symbolic approach including neural networks and perception.

 

Objectives:

·         To understand some non-classical logics including nonmonotonic reasoning, fuzzy logic, and probabilistic reasoning with uncertainty

·         To program an expert system using a preexistent expert system shell and your own unique knowledge rule base.

·         To grasp the dominant areas of machine learning including version space, inductive logic programming, genetic algorithms, clustering, and neural networks

·         To study some of the fundamentals of natural language processing

·         To understand the earliest algorithm of Swarm Programming:  shortest path mimicking ants

·         To program the techniques and algorithms studied in class into working systems

Subject Matter   (Tentative list and schedule of coverage):

Week

Date

Topics

Current Program

1

1- Tues, 1/18/11

Course Introduction; 

Philosophical Foundations of AI;

Logic Revisited; PROLOG Revisited  

PROLOG Basics

2 -Thur, 1/20/11

Advanced PROLOG;

The Logic of Paradoxes;

Prolog programming of paradoxes

(Individual)

2

3- Tues, 1/25/11

More PROLOG; Nonmonotonic Logics; Review of JTMS / Stable Models

PROLOG Paradoxes

4- Thur, 1/27/11

Ideas on Implementation of JTMS;

Demonstration of How to Present a Paper: Paper on Nonmonotonic Reasoning and Stable Models   

(Group)

3

5- Tues, 2/1/11

 

Quiz

Quiz

Paper on PROLOG

Fuzzy Sets and Fuzzy Logics;

Implementation of JTMS

6- Thur, 2/3/11

 

 

Fuzzy Logic Systems;  Expert Systems;  Systems of Uncertainty

(Group – Multiple Parts and Due Dates)

4

 

 

** Mon 2/7/11

Last day to withdraw without record

 

7- Tues, 2/8/11

 

Paper on Fuzzy Logic Systems

Introduction to Planning

 

8- Thur, 2/10/11

 

Paper on Systems of Uncertainty

More Planning

 

5

9   - Tues, 2/15/11

Paper on Planning – 1;      

Knowledge Discovery and Data Mining

 

10 - Thur, 2/17/11

 

Paper on Planning – 2;

Machine Learning – Inductive Logic Programming

 

6

11- Tues, 2/22/11

Paper on Data Mining

Machine Learning – Decision Tree Learning

 

12- Thur,  2/24/11  

Review for Midterm

Paper on Inductive Logic Programming

Machine Learning – Association Rule Mining

 

7

13- Tues, 3/1/11

Midterm 1

Decision Tree Learner

14- Thur,  3/3/11

        No Class

Midterm Break – No Class

(Group – Multiple Parts and Due Dates)

8

15- Tues, 3/8/11

Paper on Decision Tree Mining

Paper on Association Rule Mining

Introduction to Evolutionary Computation;  Genetic Algorithms

 

16- Thur, 3/10/11

Genetic Programming;  Grammatical Evolution

 

9

18- Tues, 3/15/11

Paper on Genetic Algorithms – 1

Paper on Genetic Algorithms - 2

Communication:  The Underpinnings of Natural Language Understanding (NLU)-

 

19- Thur, 3/17/11

Paper on Genetic Programming

Grammars in Natural Language Understanding (NLU) ---Chap 22

 

10

20- Tues, 3/22/11

Paper on Grammatical Evolution

 

Semantics and Pragmatics in NLU

NLU System

21- Thur, 3/24/11

Thought Chunking;  Guest Speaker on an NLU application for the Hearing Impaired

(Individual)

11

22- Tues, 3/29/11

Paper on Natural Language Understanding-1

Introduction to  IR / Web Mining

 

23- Thur, 3/31/11

Paper on Natural Language Understanding-2

Swarm Intelligence

Lego Robot System

12

**  Mon, 4/4/11

Last day to withdraw with grade of  ‘W’

 

24- Tues, 4/5/11

 

 

Paper on Web Mining

Vision and Perception

(Group – Multiple Parts and Due Dates)

25- Thur, 4/7/11

 

Paper on Swarm Intelligence

Introduction to Robots

 

13

26- Tues, 4/12/11

Paper on Vision and Perception

Paper on Robots

More Robots

 

27- Thur, 4/14/11

Paper on Web bots

Additional Paper-1;

Review for Midterm 2

 

14

28 - Tues, 4/19/11

Midterm 2

Test on material covered since last exam

 

29- Thur, 4/21/11

Easter Break – No Class

 

15

30- Tues, 4/26/11

Additional Paper-2;

Graduate Projects

 

31- Thur, 4/28/11

 

Robot Talent Show!

 

16

Tuesday,  5/2/11

4:30-6:20pm

 Cumulative AI Final

 Miriam Hall 203

 

Saturday, 5/7/11

Graduate Student

GRADUATION 12:45pm

 

Sunday, 5/8/11

Undergraduate Student

GRADUATION 9:45am

 

 

 

Suggested Text:        

Artificial Intelligence  3rd Edition; 

Elaine Rich, Kevin Knight, Shivashankar B. Nair

 

 

Suggested Additional  Text:

         Artificial Intelligence A Modern Approach 

By, Stuart Russell and Peter Norvig

ISBN # 0-13-103805-2                      

  

Grading Undergraduate Students (Approximate distribution of credit): 

Paper Presentation                                          10%

Midterm #1 –                                                              16%

Midterm #2 –                                                  17 %

Final Exam –                                                   18%

            Homework and Programming Assignments   30%

            Quiz                                                                05%

            In-Class Grade                                                04%

 

                                   

Grading Graduate Students (Approximate distribution of credit): 

Paper Presentation                  08 %

Midterm #1 –                         14 %

Midterm #2 --                          15 %

Final Exam –                           18 %

            Assignments                            25 %

            Graduate Project                     14 %

            Quiz                                        4%

            In-Class Grade                        2 %

                       

 

Graduate Student Project

Graduate students are required to produce a final project for the course.  This entails choosing a topic of Artificial Intelligence not presented in class (or extending what was presented in class) and doing the following:

1.      read at least two articles on the topic

2.      write a short term paper (4 pages) in your own words describing the topic

3.      write a software program or hardware project demonstrating some aspect of the topic

4.      present your paper in a 10-15 minute Powerpoint presentation to the class

5.      demonstrate your simulation or demonstration object to the class in a 5-10 minute demo

6.      Submit term paper, Powerpoint slides, simulation/demonstration object

 

 

Policy on Makeups, Missed and Late Work:

1.      Late Work:  Work will usually be accepted late and recorded as such. Work is due at the beginning of class.  A 10% penalty is applied for every class day the assignment is late.  No work will be accepted after solutions have been given out, or after the assignment has been graded and returned.

2.      Make-ups:  Tests are expected to be taken on the test date.  Any make-ups must be established with me ahead of time.  There are no make-ups for in-class pop quizzes, exercises, or participation.  To get these points, you must come to class.  

3.      Attendance: Students are expected to come to class.  If a class must be missed, however, students are responsible for all material, assignments, and announcements made during class.  For this reason, you are encouraged to find a colleague with whom you can communicate to share such important information.

Programming Conduct Rules:

¨      Programming assignments are dispensed to reinforce concepts presented in class.  Good programming skills comprise a fundamental component of being a computer scientist.    Assignments in this class are short enough to write by yourself.  As I am trying to endow in you the fundamental techniques and algorithms of artificial intelligence, no graphical user interface (GUI) is necessary or required.

¨      Students may share ideas in composing programs, but may not code them together.  There is no sharing of code, only ideas.  Any collaborative work should be acknowledged in the comments.  Plagiarizing code will result in a zero for the program.

 

Email Communication and Class Computer Accounts:

·         Email:  I prefer to conduct communication through email.  My email address (as indicated above) is seitzer@.udayton.edu.  Please feel free to write me anytime.  I try to check my email many times through the day.  If you do not have an email account, I ask that you get one.  Student email accounts can be acquired from the Systems Administrator.  For information, you may call (937)229-3858.

 

·         Lab Work and Programs: Programming assignments may be written using the platform of your choice in any lab of your choice so long as the system on which you are working has an operational C , C++, or Java compiler.

 

Course Web Pages and Isidore Site:

·         The course has its own web page that can be found at URL http://homepages.udayton.edu/~jseitzer1/cps481.  The majority of the class work, assignments, and handouts will be posted on http://isidore.udayton.edu.

 

Class Email List:

·         Along with web page postings, I regularly send my classes email via the respective Class Email List.   Please make sure you have the correct address logged with the university to receive all class emails.  These lists are maintained by the university.

University of Dayton Honor Code
The University of Dayton Academic Honor Code: A Commitment to Academic Integrity

I understand that as a student of the University of Dayton, I am a member of our academic and social community, I recognize the importance of my education and the value of experiencing life in such an integrated community,  I believe that the value of my education and degree is critically dependent upon the academic integrity of the university community, and so in order to maintain our academic integrity, I pledge to: 
 
- Complete all assignments and examinations by the guidelines given to me by my instructors,

- Avoid plagiarism and any other form of misrepresenting someone else's work as my own

- Adhere to the Standards of Conduct as outlined in the Academic Honor Code.

 

In doing this, I hold myself and my community to a higher standard of excellence, and set an example for my peers to follow. 
 
Signed:                      
Dated: