Neural network for image Fourier transform classification

Considers the performance of a neural-network (NN)-based visual control system with NNs of different types (multilayered perceptrons and Hamming nets). They discuss the possible compensation of disturbances arising in a coherent-optical processor by NN learning. Simulation shows that different NNs have different behaviors for two types of input distorted data: the perceptron NN is more suitable for compensation of optical tract errors while the winner-takes-all NN performs better for noise damaged input patterns. >