Complexity reduction of singleton based neuro-fuzzy algorithm

Peter Baranyi, Kin fong Lei, Yeung Yam

Research output: Contribution to journalConference article

22 Citations (Scopus)

Abstract

During the past few years efficient singular value-based complexity reduction tools have been developed to fuzzy logic techniques. This paper introduces a singular value-based reduction method to the generalised type neural network. The method conducts singular value decomposition of the weighting functions defined on the connections among the neurons and generates certain linear combinations of the original weighting functions to form a new connection-net for the complexity reduced neural network.

Original languageEnglish
Pages (from-to)2503-2508
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume4
Publication statusPublished - Dec 1 2000
Event2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA
Duration: Oct 8 2000Oct 11 2000

    Fingerprint

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Hardware and Architecture

Cite this