The model of multifunctional neural element of intelligent systems

Abstract

The article shows the features of realization of multioperand processing in neural structures on the base of difference cuts, that allow to expand functional capabilities and to reduce time consumptions in neural processing. The structural organization of the parallel-pipeline processor for neural-like vector data processing on the DCs base are proposed. This parallel-pipeline processor on CPLD base are implemented, which allow realize neural chip with a fragment of the neural network layer.