Implementation of the Hopfield model with excitatory and inhibitory synapses and static thresholding

Amanda J. Breese; John Macdonald

doi:10.1117/12.21191

Translator Disclaimer

1 August 1990 Implementation of the Hopfield model with excitatory and inhibitory synapses and static thresholding

Proceedings Volume 1294, Applications of Artificial Neural Networks; (1990) https://doi.org/10.1117/12.21191
Event: 1990 Technical Symposium on Optics, Electro-Optics, and Sensors, 1990, Orlando, FL, United States

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. .

Citation Download Citation

Amanda J. Breese and 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); https://doi.org/10.1117/12.21191

ACCESS THE FULL ARTICLE