On the Power of Networks of Majority Functions

Quantization of the synaptic weights is a central problem of hardware implementation of neural networks using 0 technology. In this paper, a particular linear threshold boolean function, called majority function is considered, whose synaptic weights are restricted to only three values: ?1, 0, +1. Some results about the complexity of the circuits composed of such gates are reported. They show that this simple family of functions remains powerful in term of circuit complexity. The learning problem with this subclass of threshold function is also studied and numerical experiments of diierent algorithms are reported.