Accession Number : ADP008664

Title :   Learning in Optical Neural Networks,

Corporate Author : CALIFORNIA INST OF TECH PASADENA DEPT OF ELECTRICAL ENGINEERING

Personal Author(s) : Psaltis, Demetri

Report Date : 22 MAY 1992

Pagination or Media Count : 2

Abstract : In this paper we will review recent advances in training optical neural networks. We will focus on holographic implementations using photorefractive crystals. The vast majority of learning algorithms in neural networks are based on some form of generalized Hebbian Learning. With Hebbian learning the strength of the connection between two neurons is modified in proportion to the product (or possibly some other function) of the activation functions of the two neurons. These activation functions are typically the neuron response and error signals. The multiplicative Hebbian rule can be implemented if the hologram that connects two neurons is formed as the interference of two light beams generated by the two neurons. This simple and elegant method for training an individual connection can also form the basis for training large optical networks.

Descriptors :   *NEURAL NETS, *HOLOGRAPHY, *LEARNING, HOLOGRAMS, ALGORITHMS, VERY LARGE SCALE INTEGRATION.

Subject Categories : Cybernetics
      Holography

Distribution Statement : APPROVED FOR PUBLIC RELEASE