Continual neural networks

It is necessary to introduce many parameters describing structure and input signal of pattern recognition system during construction of open-loop structures of multilayer neural networks in order to provide maximum probability of correcting recognition in practice. Availability of great number of parameters, viz. hundreds and thousands, rouses some difficulties for learning and technical implementation of such multilayer neural network. Essence of introduction of continual properties of multilayer neural network characteristics includes the following: vector {x_i, i=1, ..., I} replaces by function x(i) of continued argument, i.e. during transition to continuum of characteristic value. Transition to attributes continuum and continuum of neurons in layer is considered on the concrete examples of neural networks structures.