Sigma-Pi Neural Networks:Error Correction Methods
Larisa Adol'fovna Lyutikova · Procedia Computer Science · 2018
This paper considers the application of logical error correction methods for ΣΠ-artificial neural networks within classification problems. The logical methods are widely used in the detection of implicit regularities in a domain under study. We propose a technique to reveal such regularities according to the structure of the ΣΠ-neuron. This notably improves adaptive features of the recognition system. We assert that a combined approach contributes to the recognition system performances. It allows as a solution indicating objects closest by characteristic features identified using a logical correction method to the requested ones in case of the ΣΠ-neurons incorrect response.