Space-time sharing optical neural network

Abstract

The massive interconnection and parallel operation in an optical neural network (ONN) require a high-resolution, large-dynamic-range spatial light modulator (SLM) for the construction of the interconnectionweight matrix (IWM). However, the resolution of currently available SLM's is limited, and this is a major obstacle in the development of a large-scale optical neural computers. We use a space-time-sharing technique to improve the resolution of an optical neural operation. Because the ONN we recently developed1 uses incoherent light, the space–bandwidth product of the network can be expanded by space-time multiplexing. In other words, a large-scale neural operation can be accomplished with a smaller network, by trading off the processing speed. To accomplish this task, we have shown that a large-scale IWM can be partitioned into arrays of sub-IWM's, of which the space–bandwidth product of the sub-IWM's is equal to the number of neurons in the neural network. Then by sequentially displaying these arrays of sub-IWM's, a larger (nfold) space–bandwidth image pattern can be obtained by using a smaller ONN. Computer-simulated results and experimental demonstrations are also provided in this paper.