Removal of hidden units and weights for back propagation networks

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

26 Citations (Scopus)

Abstract

The objective of this paper is to present a simple and effective method for removal of both hidden units and weights. In this paper, we propose two methods, 'Consuming energy' method and 'Weights power' method, and compare them with the conventional method. According to our computer simulations using the mirror symmetry problem, the Weights power method has shown the best performance in respect of size reduction (removal of units and weights), generalization performance, and the amount of computation required. For example, the number of hidden units reduced to about 40% of the initial state, and the number of weights reduced to less than a fourth of the initial state. In addition, generalization performance was improved more than 10%.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages351-353
Number of pages3
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1993 Dec 1
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
Duration: 1993 Oct 251993 Oct 29

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume1

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CityNagoya, Jpn
Period93/10/2593/10/29

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Removal of hidden units and weights for back propagation networks'. Together they form a unique fingerprint.

  • Cite this

    Hagiwara, M. (1993). Removal of hidden units and weights for back propagation networks. In Proceedings of the International Joint Conference on Neural Networks (pp. 351-353). (Proceedings of the International Joint Conference on Neural Networks; Vol. 1). Publ by IEEE.