To read the full version of this content please select one of the options below:

Non‐linear Processing in Artificial Synapses

Alejandro B. Engel (Rochester Institute of Technology, New York, USA)

Kybernetes

ISSN: 0368-492X

Article publication date: 1 January 1992

Abstract

Analyses the possibility of allowing non‐linear synaptic processing in Artificial Neural Networks (ANN) both theoretically and practically. The simple computer simulations described strongly suggest that this is a viable alternative, and preferable to ANN with just linear synapses, because of the savings in hardware (fewer components are needed) and software (reduction in training time) when dealing with similar problems. Derives some considerations regarding a possible relationship between the parallel processor proposed and living nerve cells.

Keywords

Citation

Engel, A.B. (1992), "Non‐linear Processing in Artificial Synapses", Kybernetes, Vol. 21 No. 1, pp. 35-45. https://doi.org/10.1108/eb005916

Publisher

:

MCB UP Ltd

Copyright © 1992, MCB UP Limited