CSCI 6962   -   Soft Computing   -   Fall 2001

Tuesday 6:00-9:00pm, Ricketts 212


Instructors: Bill Cheetham, Kai Goebel 

TA: tba

Office: Amos Eaton 218


Office Hours: TBA 


Phone: 387-5222 (Bill), 387-4194 (Kai)





“Neuro-Fuzzy and Soft Computing”
 J.-S.R. Jang, C.-T. Sun, E. Mizutani;
 Prentice Hall, 1997

“Applying Case-Based Reasoning”,
 I. Watson; Morgan Kaufman Publishers,

Course Description

This course introduces soft computing methods which, unlike hard computing, are tolerant of imprecision, uncertainty and partial truth. This tolerance is exploited to achieve tractability, robustness and low solution cost. The principal constituents of soft computing are fuzzy logic, neural network theory, and probabilistic reasoning. The course studies the methods and explores how they are employed in associated techniques such as Case-Based Reasoning and expert systems for pattern recognition, clustering, diagnosis, and control both individually and in hybrid arrangement. The basics of each technique will be discussed and industrial applications will illustrate the strengths of each approach. The course is self-contained. Knowledge of calculus and familiarity with a high-level programming language is assumed. The class will have several programming and homework assignments, and a final project.

Syllabus and Lecture Viewgraphs

Paper Presentation Schedule

Final Project Presentation Schedule


Conferences (target your final paper for one of these or another conference)

1st European Conference on Case-Based Reasoning, Aberdeen, Scotland, September 2002

others TBA

Presentation Schedule



  Homework 65%

  Presentation of a selected paper 5%

  Project 30%

Academic Integrity (from Edwin Rogers)

Relationships between instructor and student and among students are built on trust. For instance, students must trust that the instructor has made appropriate decisions about the structure and content of the course, and the instructor must trust that the work turned in by students is their own or done in fair proportion with their partners. Moreover, students must trust that their peers treat them fairly in reviewing drafts, and that their teammates will give their best effort on joint work.

Most importantly, being trusted makes one responsible to live up to that trust. Violation of this responsibility undermines the educational process.

The Rensselaer Handbook defines various forms of academic dishonesty and procedures for dealing with them. All forms are violations of trust. Students should familiarize themselves with this portion of the Rensselaer Handbook and note that the penalties for plagiarism and other forms of cheating can be quite harsh.

Each assignment must be your own work or the work of your own team. Clearly, discussion of an assignment with others is permitted, but the work of this class is largely open-ended and creative. You will get the most out of it and enjoy it most, if you pursue your own ideas.

Guidelines for working together

  you may discuss approaches with each other

  you may give each other hints

  you can not give solutions

  you can not look at / copy each others answers / code

The penalty for any act of flagrant academic dishonesty is an F for the course.

August 27, 2001;