A Genetic Algorithm Based Variable Structure Neural Network

S. H. Ling, H. K. Lam, Hung Fat Frank Leung, Y. S. Lee

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

6 Citations (Scopus)

Abstract

This paper presents a neural network model with a variable structure, which is trained by genetic algorithm (GA). The proposed neural network consists of a Neural Network with a Node-to-Node Relationship (N4R) and a Network Switch Controller (NSC). In the N4R, a modified neuron model with two activation functions in the hidden layer, and switches in its links are introduced. The NSC controls the switches in the N4R. The proposed neural network can model different input patterns with variable network structures. The proposed neural network provides better result and learning ability than traditional feed forward neural networks. Two application examples on XOR problem and hand-written pattern recognition are given to illustrate the merits of the proposed network.
Original languageEnglish
Title of host publicationIECON Proceedings (Industrial Electronics Conference)
Pages436-441
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2003
EventThe 29th Annual Conference of the IEEE Industrial Electronics Society - Roanoke, VA, United States
Duration: 2 Nov 20036 Nov 2003

Conference

ConferenceThe 29th Annual Conference of the IEEE Industrial Electronics Society
Country/TerritoryUnited States
CityRoanoke, VA
Period2/11/036/11/03

Keywords

  • Genetic algorithm
  • Hand-written pattern recognition
  • Neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this