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

Research output: Contribution to conferencePaper

30 Citations (Scopus)

Abstract

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).

Original languageEnglish
Pages625-630
Number of pages6
Publication statusPublished - 1990 Dec 1
Event1990 International Joint Conference on Neural Networks - IJCNN 90 - San Diego, CA, USA
Duration: 1990 Jun 171990 Jun 21

Other

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

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Novel back propagation algorithm for reduction of hidden units and acceleration of convergence using artificial selection'. Together they form a unique fingerprint.

  • Cite this

    Hagiwara, M. (1990). Novel back propagation algorithm for reduction of hidden units and acceleration of convergence using artificial selection. 625-630. Paper presented at 1990 International Joint Conference on Neural Networks - IJCNN 90, San Diego, CA, USA, .