A two-layer perceptron with 5×5 input neurons, 4×4 hidden neurons, and 2×2 output neurons is electro-optically implemented. Holographic lenslet arrays are used to implement neural interconnections, and time-sharing of single layer interconnections is utilized. In addition, an input-dependent thresholding operation is also utilized. This electro-optical multilayer perceptron is used to recognize Arabic numeral patterns and the four output neurons are binary coded.