EFFICIENT MODELING FOR MULTILAYER FEED-FORWARD NEURAL NETS.

S. Y. Kung, J. N. Hwang, S. W. Sun

Research output: Contribution to journalConference articlepeer-review

11 Scopus citations

Abstract

The authors discuss two important aspects in the multilayer feed-forward neural nets: the optimal number of hidden units per layer, and the optimal number of synaptic weights between two adjacent layers. On the basis of simulations, they conjecture that the optimal number of hidden units shall be equal to or a little bit more than M-1 for an efficient learning, where M is the number of pairs of training patterns used. Locally interconnected nets may be useful for some real applications where geometrical properties are significant. By introducing highway links into the locally interconnected nets, the convergence speed can be improved significantly.

Original languageEnglish (US)
Pages (from-to)2160-2163
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
StatePublished - 1988

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'EFFICIENT MODELING FOR MULTILAYER FEED-FORWARD NEURAL NETS.'. Together they form a unique fingerprint.

Cite this