Novel back propagation algorithm for reduction of hidden units and acceleration of convergence using artificial selection

研究成果: Paper査読

31 被引用数 (Scopus)

抄録

A novel back-propagation algorithm with artificial selection is proposed. It is effective for both fast convergence and reduction of the number of hidden units. The main feature of the proposed algorithm is detection of the worst hidden unit. This is done by using the proposed badness factor, which indicates the badness of each hidden unit. It is the sum of back-propagated error components over all patterns for each hidden unit. For fast convergence, all the weights connected to the detected worst unit are reset to small random values at a suitable time. As for the reduction of hidden units, detected bad units are erased by precendent. Computer simulation results show the effectiveness of the proposed algorithm; for example, the numbers of hidden units in the EX-OR problems converge to 2 (theoretical number).

本文言語English
ページ625-630
ページ数6
出版ステータスPublished - 1990 12 1
イベント1990 International Joint Conference on Neural Networks - IJCNN 90 - San Diego, CA, USA
継続期間: 1990 6 171990 6 21

Other

Other1990 International Joint Conference on Neural Networks - IJCNN 90
CitySan Diego, CA, USA
Period90/6/1790/6/21

ASJC Scopus subject areas

  • 工学(全般)

フィンガープリント

「Novel back propagation algorithm for reduction of hidden units and acceleration of convergence using artificial selection」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