Published in the Proceedings of the Third Ieee International Conference on Electronics Circuits and Systems Icecs Rodos Greece October a Method for All Positive Optical Multilayer Perceptrons

The most promising approaches for optical neural networks are based on intensity encoding However a serious drawback of intensity encoding is the lack of negative values and optical subtraction which are essential for rendering neural networks useful To overcome the need for optical subtraction a novel training method is described here that is es pecially useful for optical multilayer neural net works In this method subtraction is implemented as a transformation of the interconnection weights which makes possible the implementation of mul tilayer perceptrons with optical thresholding The method is straightforward to implement in optical neural networks where learning occurs under ex ternal electronic computer control