Skip to main navigation Skip to search Skip to main content

A hybrid genetic algorithm for designing feedforward neural networks

  • Xu Jinhua*
  • , Lu Yue
  • *Corresponding author for this work
  • East China Normal University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a hybrid algorithm is proposed for designing feedforward neural networks, A genetic algorithm is proposed to tune the connections and parameters between the input layer and the hidden layer, and orthogonal transformation is applied to tune the connections and parameters between the hidden layer and the output layer. The crossover operator and mutation operator are based on the singular value decomposition of the outputs of the hidden nodes. Using the proposed algorithm, both the structure and parameters of a neural network can be optimized efficiently. Simulations are presented to demonstrate the effectiveness of the proposed approach.

Original languageEnglish
Title of host publicationProceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008
Pages549-554
Number of pages6
DOIs
StatePublished - 2008
EventProceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008 - Xiamen, China
Duration: 17 Nov 200819 Nov 2008

Publication series

NameProceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008

Conference

ConferenceProceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008
Country/TerritoryChina
CityXiamen
Period17/11/0819/11/08

Fingerprint

Dive into the research topics of 'A hybrid genetic algorithm for designing feedforward neural networks'. Together they form a unique fingerprint.

Cite this