A neural network using a scalar product and defining several solutions

Abstract

The Hamming neural network is a very effective tool for solving discrete object recognition problems, the binary components of which are described using bipolar components, and the difference between the number of identical bipolar components of the vectors and the Hamming distance between them is used as a proximity measure. For a finer classification of binary objects (vectors), a number of Hamming distance extensions are used, using various affinity functions (proximity or interconnection) between binary objects. The article proposes modifications of the Hamming neural network, in which instead of the Hamming distance, other affinity functions between binary vectors are proposed. Figs.: 7. Tabl.: 2. Refs.: 8 titles. Keywords: neural network; Hamming distance; affinity functions between binary vectors; discrete objects.