Design and Demonstration of an Opto-Electronic Neural Network using Fixed Planar Holographic Interconnects

Implementation of an opto-electronic Hopfield style associative memory neural network is discussed with emphasis on the construction of an experimental system employing binary amplitude holograms. 1. Introduction A key element of most neural network systems is the massive number of weighted interconnections used to tie relatively simple processing nodes together in a useful architecture. The inherent parallelism and interconnection capability of optics make it a likely candidate for the implementation of the neural network interconnection process. While there are several optical technologies worth exploring, we are looking at the capabilities and limitations of using fixed planar holographic interconnects in a neural network system and have implemented an initial test system using planar holograms and opto-electronic nodes. 2. System All neural network systems consist of nodes (simple non-linear elements crudely imitating biological neurons) and weighted interconnections (synapses) bet..