Boolean Neural Network Design Using Set Covering in Hamming Geometrical Space

Abstract

Some novel learning strategies based on set covering in Hamming geometrical space are presented and proved, which are related to the three-layer Boolean neural network (BNN) for implementing an arbitrary Boolean function with lowcomplexity. Each hidden neuron memorizes a set of learning patterns, then the output layer combines these hidden neurons for… (More)

Topics

1 Figure or Table

Slides referencing similar topics