A Frobenius approximation reduction method (FARM) for determining optimal number of hidden units

Sun-Yuan Kung, Yu Hen Hu

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

19 Scopus citations

Abstract

A least square approximation method is proposed to reduce the number of hidden units of a trained multilayer perceptron artificial neural network structure. In this method, hidden neurons contributing the most to the net function of the output layer will be retained while the hidden units contributing the least will be removed. It is shown theoretically that the proposed method minimizes the Frobenius norm of the approximation error, hence the name Frobenius approximation reduction method (FARM). Also reported are simulation results on ECG (electrocardiogram) classifications. The results support the theoretical predictions and yield very encouraging performances.

Original languageEnglish (US)
Title of host publicationProceedings. IJCNN - International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages163-168
Number of pages6
ISBN (Print)0780301641
StatePublished - Jan 1 1992
EventInternational Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA
Duration: Jul 8 1991Jul 12 1991

Other

OtherInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
CitySeattle, WA, USA
Period7/8/917/12/91

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'A Frobenius approximation reduction method (FARM) for determining optimal number of hidden units'. Together they form a unique fingerprint.

  • Cite this

    Kung, S-Y., & Hu, Y. H. (1992). A Frobenius approximation reduction method (FARM) for determining optimal number of hidden units. In Anon (Ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks (pp. 163-168). Publ by IEEE.