Fully coupled and feedforward neural networks with complex-valued neurons

Abstract

This paper discusses neural networks with complex-valued neurons with both discrete and continuous outputs. It reviews existing methods of their applications in fully coupled associative memories. Such memories are able to process multiple gray levels when applied for image de-noising. In addition, when complex-valued neurons are generalized to take a continuum of values, they can be used as substitutes for perceptron networks. Learning of such neurons is demonstrated and described in the context of traditional multilayer feedforward network learning. Such learning is derivative-free and it usually requires reduced network architecture. The notion of a universal binary neuron is also introduced. Selected examples and applications of such networks are also referenced. © 2008 Springer-Verlag Berlin Heidelberg.