Skip to main navigation Skip to search Skip to main content

Simultaneous node pruning of input and hidden layers using genetic algorithms

  • Gi Su Heo*
  • , Il Seok Oh
  • *Corresponding author for this work
  • Jeonbuk National University

Research output: Contribution to conferenceConference paperpeer-review

Abstract

In optimizing the neural network structure, there are two methods: the pruning scheme and the constructive scheme. This paper uses the pruning scheme to optimize neural network structure. The genetic algorithm is used to find out the optimum node pruning. In the conventional researches, the input and hidden layers were optimized separately. On the contrary we attempted to optimize the two layers simultaneously by encoding two layers in a chromosome. The offspring networks inherit the weights from the parent. For learning, we used the existing error back-propagation algorithm. In our experiment with various databases from UCI Machine Learning Repository, we could get the peak performance when the network size was reduced by about 8∼25%. As a result of t-test the proposed method was shown to have a better performance, compared with other pruning or construction methods.

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC
PublisherIEEE Computer Society
Pages3428-3433
Number of pages6
ISBN (Print)9781424420964
DOIs
StatePublished - 2008
Event7th International Conference on Machine Learning and Cybernetics, ICMLC 2008 - Kunming, China
Duration: 2008.07.122008.07.15

Publication series

NameProceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC
Volume6

Conference

Conference7th International Conference on Machine Learning and Cybernetics, ICMLC 2008
Country/TerritoryChina
CityKunming
Period08.07.1208.07.15

Keywords

  • Cross-validation
  • Genetic algorithm
  • Node pruning
  • Optimization of neural networks

Quacquarelli Symonds(QS) Subject Topics

  • Computer Science & Information Systems
  • Data Science

Fingerprint

Dive into the research topics of 'Simultaneous node pruning of input and hidden layers using genetic algorithms'. Together they form a unique fingerprint.

Cite this