Skip to main navigation Skip to search Skip to main content

Artificial neural network with complex weight and its training

  • SUNY Buffalo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Artificial neural networks that use complex weights for the synaptic connections are presented. It is shown that the use of complex weights overcomes linear nonseparability for functions such as exclusive-OR and hence can be implemented using a single-layer network. The authors also present a modification to the backpropagation method to train the neural network presented. Several examples including symmetry problems, summation, and negation are presented to demonstrate the effectiveness of the use of complex weights. It is expected that this approach can implement functions of greater complexity using simpler networks (with fewer layers) than would be required with conventional approaches.

Original languageEnglish
Title of host publicationProceedings 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, RNNS 1992
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages354-361
Number of pages8
ISBN (Electronic)0780308093, 9780780308091
DOIs
StatePublished - 1992
Event1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, RNNS 1992 - Rostov-on-Don, Russian Federation
Duration: Oct 7 1992Oct 10 1992

Publication series

NameProceedings 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, RNNS 1992

Conference

Conference1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, RNNS 1992
Country/TerritoryRussian Federation
CityRostov-on-Don
Period10/7/9210/10/92

Keywords

  • Back-propagation
  • Complex Weight
  • Exclusive-OR Function
  • Linear Separability Problem
  • Neural Networks
  • Perceptron

Fingerprint

Dive into the research topics of 'Artificial neural network with complex weight and its training'. Together they form a unique fingerprint.

Cite this