A perceptron-based optical quadratic neural network using a photorefractive crystal

An optical quadratic neural network (OQNN) utilizing four-wave mixing in barium titanate (BaTi03 ) has been investigated and developed. This network implements a feedback loop using a charged-coupled device (CCD) camera, a Macintosh II microcomputer, two monochrome liquid crystal televisions (LCTVs), and various optical elements. For training, the network employs the supervised quadratic perceptron algorithm to associate binary-valued input vectors with specified target vectors. Using a spatial multiplexing scheme for two bipolar neurons, the quadratic network was able to associate an input vector with various target vectors. In addition, the network was reconfigured to discriminate two different input patterns simultaneously. Both analytical and experimental results are presented.