Syllabus

Applied Intelligent Reasoning Systems - Syllabus

Instructor Name: Kai Goebel , Bill Cheetham

Office: None (office hours after class)

Telephone: Kai 387-4194, Kai Goebel

Email: goebel@cs.rpi.edu; cheetham@crd.ge.com

Further details are available through RPI’s WebCT at this URL

Course Description

This course explores different methods for automated decision making. You will learn various decisioning techniques, see real world examples, then implement each technique. The course introduces concepts from soft computing (fuzzy logic, neural nets, genetic algorithms, Dempster Shafer, hybrid systems, etc.), information fusion, case-based reasoning, neuroscience, and knowledge management. Knowledge of calculus and familiarity with a high-level programming language are required. Knowledge of matlab® is a plus because most homework assignments will involve using matlab®.

Resources

“Neuro-Fuzzy and Soft Computing” J.-S.R. Jang, C.-T. Sun, E. Mizutani; Prentice Hall, 1997 - required
“Applying Case-Based Reasoning”, I. Watson; Morgan Kaufman Publishers, 1997- optional

top

Introduction

This course explores different methods for automated decision making.You will learn various decisioning techniques, see real worldexamples, then implement each technique. The course introduces concepts from soft computing (fuzzy logic, neural nets, geneticalgorithms, Dempster Shafer, hybrid systems, etc.), information fusion, case-based reasoning, neuroscience, and knowledge management. Knowledge of calculus and familiarity with a high-level programming language are required. Knowledge of matlab® is a plus because most homework assignments will involve using matlab®.There is a semester project.

top

Attendance / Policies

Assignments are due at the beginning of class.
The syllabus and all accompanying dates are subject to change at any time; all such changes will be announced in class and updated on this web page.
Cooperative efforts at understanding the material conceptually are encouraged. However, all written work and programs you turn in must be your own. You may not share solutions. Submitting work that is not your own is considered cheating, as per RPI policy.
If you can't come for scheduled office hours, please send us email; we would be happy to schedule a meeting at some other mutually agreed upon time.

top

Projects

To be developed

top

Exams/Grading

Homework 60%
Presentation of a selected paper 5%
Project 30%
Class participation 5%

top

Honesty

The evaluation of student performance is a service provided by Rensselaer. Attempts to undermine this service lower Rensselaer's reputation. Therefore, it is essential that academic honesty be preserved. Unless otherwise indicated, you should cooperate with one another in and outside of class on the solution of problems. You may collaborate with your partner on reports. However, you may not collaborate on examinations or misrepresent another person's work as your own on examinations. You may not bring crib sheets to examinations, and you may not write on or alter examination materials that you submit for regrading. Students who violate the spirit or letter of these rules are subject to penalties according to the principles outlined in the Rensselaer Student Handbook.

top

Schedule

Session/ Date	Topics/Readings/ References/ Links	Assignments/Labs/ Exercises/Exams
August 30	Course Description Where we work Introduction: What is an intelligent Decision System Matlab tutorial Fuzzy Sets
September 6	Fuzzy Reasoning; Fuzzy Inference; (Fuzzy) Clustering
September 13	Rulebase Structure Identification; Clustering; Applications of Fuzzy Logic
September 20	Fuzzy Diagnosis Fuzzy Data Fusion
September 27	Gradient descent optimization: least squares methods Genetic Algorithms – Guest speaker: Tom Kiehl in-class exercise: class acts as GA Applications of GA's
October 4	Neural Nets Supervised Learning Reinforcement Learning Unsupervised Learning
October 11	NO CLASS – Follow Monday Schedule Today
October 18	Theoretical Neuroscience Case-Based Reasoning
October 25	Applications of CBR
November 1	Applications of CBR
November 8	Applications of Neural Nets Hybrid Systems Principles of Prognostics
November 15	Principles of Information Fusion Dempster-Shafer Reasoning Multiple Classifier Fusion Systems
November 22	Baysian Belief Networks – demo Determining when to use a technique Knowledge Management Things you don’t learn in College
November 29	One-on-one project discussions
December 6	Presentations & Pizza

top

Date Last Revised: 8/11/2005