Abstract: A neural network has inputs formed by square array of optical modulators M.sub.ij and outputs by optical detectors D.sub.ij coupled to threshold comparators. A holographic plate includes a spatial modulator whose elements are controlled by a controller to form an array of optical beams from a coherent optical source. Each optical beam optically interconnects a modulator M.sub.ij with a respective detector D.sub.ij. The weight values of the neural network are provided by the intensities of the optical beams. This obviates the need for an optical weighting mask between an array of light emitting diodes and a detector array allowing a higher density of lower power consumption components and reprogrammability of the network.

Abstract: An opto-electronic component comprises a substrate of InP (4, 5) with stacks of quantum wells (6) grown on both surfaces of the substrate. Layers (7) of n doped InP having p-doped regions (8) are formed on the outer surface of the quantum well structures. In use, voltages V1 and V2 may be applied to electrodes (1) enabling the component to be used for a number of applications, e.g. as a detector/modulator pair, in close coupled arrays of modulators, etc.