Knowledge simplification of hierarchical neural network for multidimensional pattern recognition problems

Satoru Suzuki, Yasue Mitsukura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The purpose of this study is to delete the redundant connections of hierarchical neural network constructed for solving pattern recognition problem with images. The performance of neural network changes depending on the number of hidden units. For example, a lot of hidden units cause the over-fitting problem and make it difficult to understand the role of hidden units. In order to diminish the redundant connections, we propose the connection elimination method by using genetic algorithm. Firstly, walsh-hadamard transform is applied to images for feature extraction. Secondly, neural network is trained with extracted features based on back-propagation algorithm. Finally, redundant connections are eliminated by optimization processing with genetic algorithm. In order to show the effectiveness of the proposed method, computer simulation is performed for face recognition examples. From the simulation results, it was confirmed that our proposed method was useful for eliminating redundant connections of neural network, maintaining recognition performance at high level.

Original languageEnglish
Title of host publicationProceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers
PublisherSociety of Instrument and Control Engineers (SICE)
Pages1050-1054
Number of pages5
ISBN (Print)9784907764364
Publication statusPublished - 2010 Jan 1
Externally publishedYes

Publication series

NameProceedings of the SICE Annual Conference

Keywords

  • Genetic algorithm
  • Neural network
  • Walsh-hadamard transform

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Knowledge simplification of hierarchical neural network for multidimensional pattern recognition problems'. Together they form a unique fingerprint.

Cite this