LECTURE #9: FUZZY LOGIC & NEURAL NETS



Monday 26, 2004

DSES-4810-01 Intro to COMPUTATIONAL INTELLIGENCE

& SOFT COMPUTING

Instructor: Prof. Mark J. Embrechts (x 4009 or 371-4562) (embrem@rpi.edu)

Office Hours: Thursday 1-2 pm (CII5217)

Or by appointment.

Class Time: Monday/Thursday: 8:30-9:50 (Amos eaton hall 216)

TEXT (optional): J. S. Jang, C. T. Sun, E. Mizutani, “Neuro-Fuzzy and Soft Computing,” Prentice Hall, 1996. (1998) ISBN 0-13-261066-3

LECTURES #4&5: INTRO to FUZZY LOGIC

Fuzzy logic is an extension of Boolean logic and is a powerful tool for CI (computational intelligence) applications and expert systems. Fuzzy logic could and often should be combined with traditional neural network algorithms. This lecture will explain the basic idea of fuzzy logic and illustrate some examples how fuzzy logic can be applied to solve problems. Neural networks can be combined with fuzzy logic in a variety of ways. A recommended book on the subject is:

Fuzzy Engineering

Bart Kosko

Prentice Hall, 1997 (ISBN 0-13-124991-6)

Lotfi A. Zadeh is generally credited with the invention of fuzzy logic. The basis for fuzzy logic was in a sense anticipated by the philosopher Max Black in 1937 with his concept of three-valued logic. Infinite value logic developed by the Polish mathematician Lukasiewicz in the early 1930s is a generalization of three-valued logic and a predecessor of what Zadeh named fuzzy logic.

A highly recommended book (and former general bestseller in the UK) that playfully introduces the reader to fuzzy concepts can be found at under:

Fuzzy thinking

Bart Kosko

Prentice Hall (1993).

Handouts:

1. Earl Cox, “Solving problems with fuzzy logic,” AI Expert, pp. 28 - 37 (March 1982).

2. Lotfi A. Zadeh, “The Calculus of Fuzzy If / Then Rules,” AI Expert, pp. 23-27 (March 1992).

Deadlines

January 22 Homework Problem #0 (web browsing)

January 29 Project Proposal

................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download