Implementation of a multilayer perceptron network using an optically addressed photoconductive array

A two-dimensional amorphous silicon photoconductor array and a liquid crystal display form the core components of a hardware system for implementation of a multilayer perceptron neural network. All connections between layers, as well as the nonlinear transfer characteristics associated with the hidden- and output-layer neurons, are implemented in analog circuitry so that the network, once trained, behaves as a stand-alone processor. The network is shown to train very successfully, using a standard backpropagation training algorithm, on the classification of handwritten digits. A computer simulation of the hardware network is described. Excellent agreement is shown between the results of the hardware network and those of the computer simulation