CONTROL METHOD OF NEUROPROCESSOR RESPONSE TO INPUT SIGNALS Russian patent published in 2020 - IPC G06N7/00 G06N20/00 

FIELD: neurocybernetics.

SUBSTANCE: invention can be used as a functional unit of various artificial neural networks. Said result is achieved due to the fact that taking into account nonlinear properties of the object classes separation surface in N-dimensional continual space, the neuroprocessor (NP) performs linear approximation of functions in the subareas of the domain Ω, and parameters of the neuroprocessor are adjusted by training based on experimental or theoretical data on behavior of the neuroprocessor at given points of the N-dimensional continual space. When teaching the neuroprocessor to the training input, the reference signals d₁, d₂,…, d_s, and signaling inputs of NP are supplied with corresponding stimuli x₁, x₂,…, x_N. Reference signals are selected so that at least one training sample is located in each subarea Ω^*εΩ. In repetition of epochs, minimization of function errors at vertices of N-dimensional cube, which limits each subarea Ω^*.

EFFECT: technical result is to eliminate the problem of unreachable separation of nonlinearly inseparable classes by known models of neurons.

1 cl, 4 dwg