BACK-PROPAGATION LEARNING AND NONIDEALITIES IN ANALOG NEURAL NETWORK HARDWARE

We present experimental results of adaptive learning using an optically controlled neural network. We have used example problems in nonlinear system identification and signal prediction, two common areas of potential neural network application, to study the capabilities of analog neural hardware. These experiments investigate the effects of a variety of nonidealities typical of analog hardware systems. They show that networks using large arrays of nonuniform components can perform analog computations with a much higher degree of accuracy than might be expected, given the degree of variation in the network's elements. We have also investigated effects of other common nonidealities, such as noise, weight quantization, and dynamic range limitations.