. All-optical multilayer perceptrons differ in various ways from the ideal neural network model. Examples are the use of non-ideal activation functions which are truncated, asymmetric, and have a non-standard gain, restriction of the network parameters to non-negative values, and the limited accuracy of the weights. In this paper, a backpropagation-based learning rule is presented that compensates for these non-idealities and enables the implementation of all-optical multilayer perceptrons where learning occurs under control of a computer. The good performance of this learning rule, even when using a small number of weight levels, is illustrated by a series of computer simulations incorporating the non-idealities. 2 IDIAP--RR 97-02 1 Introduction An important feature of multilayer perceptrons (MLPs) is their massive parallelism of weighted interconnections between layers of non-linear processing elements. Conventional digital computers, however, cannot take advantage of the parallel...