Adaptive optical system for neural computing

Abstract

The authors deal with an adaptive optical neural network using Kohonen's self-organizing feature map algorithm for unsupervised learning. It is shown that the optical neural network is capable of performing both unsupervised learning and pattern recognition operations simultaneously, by setting matching scores in the learning algorithm. By using a slower learning rate, the construction of the memory matrix becomes topologically more organized. By introducing forbidden regions in the memory space, the neural network would be able to learn new patterns without erasing the old ones. Test results provided show the success of the technique. >