Multiplication units in feedforward neural networks and its training

Dazi Li, K. Hirasawa, Takayuki Furuzuki, J. Murata

研究成果: Conference contribution

6 被引用数 (Scopus)

抄録

This paper proposes the application of neural networks with multiplication units to parity-N problem, mirror symmetry problem and a function approximation problem. It is clear that, higher-order terms in neural networks, such as sigma-pi unit, can improve the computational power of neural networks considerably. But how the real neurons do this is still unclear. We have used one multiplication unit to construct full higher-order terms of all the inputs, which was proved very efficient for parity-N problem. Our earlier work on applying multiplication units to other problems suffered from the drawback of gradient-based algorithm, such as backpropagation algorithms, for being easy to stuck at local minima due to the complexity of the network. In order to overcome this problem we consider a novel random search, RasID, for the training of neural networks with multiplication units, which does an intensified search where it is easy to find good solutions locally and a diversified search to escape from local minima under a pure random search scheme. The method shows its advantage on the training of neural networks with multiplication units.

本文言語English
ホスト出版物のタイトルICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
出版社Institute of Electrical and Electronics Engineers Inc.
ページ75-79
ページ数5
1
ISBN(印刷版)9810475241, 9789810475246
DOI
出版ステータスPublished - 2002
外部発表はい
イベント9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
継続期間: 2002 11月 182002 11月 22

Other

Other9th International Conference on Neural Information Processing, ICONIP 2002
国/地域Singapore
CitySingapore
Period02/11/1802/11/22

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 情報システム
  • 信号処理

フィンガープリント

「Multiplication units in feedforward neural networks and its training」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル