Continual neural networks

It is necessary to introduce many parameters describing the structure and input signal of a pattern recognition system during the construction of open-loop structures of multilayer neural networks in order to provide maximum probability of correct recognition in practice. The availability of a large number of parameters, i.e., hundreds and thousands, poses some difficulties for learning and for the technical implementation of such networks. A transition to an attributes continuum and a continuum of neurons in the layer is considered for some specific neural network structures.< >