A reconfigurable fuzzy neural network with in-situ learning

W. Pedrycz; C. Hart Poskar; P.J. Czerowski

doi:10.1109/40.400639

Back

A reconfigurable fuzzy neural network with in-situ learning

Journal article

Peer reviewed

A reconfigurable fuzzy neural network with in-situ learning

W. Pedrycz, C. Hart Poskar and P.J. Czerowski

IEEE MICRO, Vol.15(4), pp.19-30

01/08/1995

DOI: https://doi.org/10.1109/40.400639

Abstract

Computer architecture

Computer networks

Field programmable gate arrays

Fuzzy logic

Fuzzy neural networks

Fuzzy set theory

Fuzzy sets

Logic devices

Multiprocessor interconnection networks

Neurons

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.< >

Metrics

1 Record Views

Details

Title: A reconfigurable fuzzy neural network with in-situ learning
Creators - without role: W. Pedrycz - University of Manitoba
C. Hart Poskar - University of Winnipeg
P.J. Czerowski - University of Winnipeg
Publication Details: IEEE MICRO, Vol.15(4), pp.19-30
Publisher: IEEE
Identifiers: 9936424508331
Academic Unit: King Abdulaziz University
Language: English
Resource Type: Journal article