A reconfigurable fuzzy neural network with in-situ learning

Author

Pedrycz, Witold ; Poskar, Hart C. ; Czerowski, P.J.

Author_Institution

Dept. of Electr. & Comput. Eng., Manitoba Univ., Winnipeg, Man., Canada

Volume

15

Issue

4

fYear

1995

fDate

8/1/1995 12:00:00 AM

Firstpage

19

Lastpage

30

Abstract

Our reconfigurable fuzzy processor (RFP) implements both aggregative and referential operations. Its architecture combines structural and parametric flexibility in a network implementing RFPs as a collection of fuzzy neurons. A fuzzy neural network using a bidirectionally linked series of shared buses facilitates a modular and scalable design environment for the RFP. An appropriate interface, separate from the RFP neuron itself, promotes the reuse of the neuron design with alternative interconnection networks

Keywords

fuzzy logic; learning (artificial intelligence); neural net architecture; neural nets; aggregative operations; bidirectionally linked series; fuzzy neurons; in-situ learning; reconfigurable fuzzy neural network; reconfigurable fuzzy processor; referential operations; scalable design environment; shared buses; Computer architecture; Computer networks; Field programmable gate arrays; Fuzzy logic; Fuzzy neural networks; Fuzzy set theory; Fuzzy sets; Logic devices; Multiprocessor interconnection networks; Neurons;

fLanguage

English

Journal_Title

Micro, IEEE

Publisher

ieee

ISSN

0272-1732

Type

jour

DOI

10.1109/40.400639

Filename

400639