1 August 1990 Implementation of the Hopfield model with excitatory and inhibitory synapses and static thresholding
Author Affiliations +
Abstract
Optical implementations of neural networks based on the Hopfield model have always found it difficult to produce the negative weights required for the interconnecting synaptic matrix. One solution involves the addition of a positive offset to the weights to ensure that they all become non-negative but this introduces another problem as a dynamic (or time-dependent) threshold value is then required which may be difficult to implement. The dynamic threshold arises out of an inconsistency in the implementation. To overcome this our implementation employs a biased (non-negative) interconnection matrix which is dynamically multiplied by a diagonal matrix version of the neural state vector so that the same biasing is experienced. The above problem then no longer arises and we are left with a static threshold value. The method is demonstrated in an optoelectronic system employing 50 fully interconnected neurons. This uses a laser source for the neurons a computer driven liquid crystal spatial light modulator to produce the interconnection weights and a photodiode array with appropriate electronic circuitry to introduced the summing and thresholding aspect. 1. .
© (1990) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Amanda J. Breese, John Macdonald, "Implementation of the Hopfield model with excitatory and inhibitory synapses and static thresholding", Proc. SPIE 1294, Applications of Artificial Neural Networks, (1 August 1990); doi: 10.1117/12.21191; https://doi.org/10.1117/12.21191
PROCEEDINGS
7 PAGES


SHARE
KEYWORDS
Neurons

Neural networks

Artificial neural networks

Brain

Photodiodes

Polarizers

Binary data

RELATED CONTENT

A face recognition method using artificial neural networks
Proceedings of SPIE (February 26 2010)
Two new classes of Boltzmann machines
Proceedings of SPIE (August 19 1993)
An Optoelectronic Neural Network
Proceedings of SPIE (February 05 1990)
Use of an eligibility trace to self-organize output
Proceedings of SPIE (August 19 1993)

Back to Top