ANALYSIS AND SYNTHESIS OF A CLASS OF DISCRETE-TIME NEURAL NETWORKS WITH MULTILEVEL THRESHOLD NEURONS

In contrast to the usual types of neural networks which utilize two st ates for each neuron, a class of synchronous discrete-time neural netw orks with multilevel threshold neurons is developed. A qualitative ana lysis and a synthesis procedure for the class of neural networks consi dered herein constitute the principal contributions of this paper. The applicability of the present class of neural networks is demonstrated by means of a gray level image processing example, where each neuron can assume one of sixteen values. When compared to the usual neural ne tworks with two state neurons, networks which are endowed with multile vel neurons will in general, for a given application, require fewer ne urons and thus fewer interconnections. This is an important considerat ion in VLSI implementation.