Removal of hidden units and weights for back propagation networks

研究成果: Conference contribution

28 被引用数 (Scopus)

抄録

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%.

本文言語English
ホスト出版物のタイトルProceedings of the International Joint Conference on Neural Networks
出版社Publ by IEEE
ページ351-353
ページ数3
ISBN(印刷版)0780314212, 9780780314214
出版ステータスPublished - 1993 12 1
イベントProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
継続期間: 1993 10 251993 10 29

出版物シリーズ

名前Proceedings of the International Joint Conference on Neural Networks
1

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

  • ソフトウェア
  • 人工知能

フィンガープリント

「Removal of hidden units and weights for back propagation networks」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