Abstract
The technical constraints typical for the logical neuroblast model and the weaknesses of the widely applied artificial neural networks are specified. The composition method of the logical network of channel switches based on the approximation of the given function by individual fragments of its domain of definition is suggested. Integral criteria are introduced in order to ensure the algorithmic simplicity of the composition of the logical network for solving arbitrarily complex problems. Walsh spectral representations are used in the synthesis algorithm. The necessary explanations are accompanied by an example.
Similar content being viewed by others
References
Zlobin, V.K. and Ruchkin, V.N., Neiroseti i neirokomp’yutery (Neironets and Neirocomputers), St. Petersburg: BKhV-Peterburg, 2011.
Sychev, A.N., Logic Neural Model Using Walsh Spectral Representations, Aut. Cont. Comp. Sci., 2011, vol. 45, no. 5, pp. 241–258
Callan, R., The Essence of Neural Networks, Prentice Hall Europe, 1999; Moscow: Vil’yams, 2003.
Sychev, A.N. and Safronov, A.P., RF Patent 2287855, Byull. Izobr., no. 32, 2006.
Barskii, A.B., Logicheskie neironnye seti: ucheb. posobie (Logic Neural Networks. A Tutorial), Moscow: BINOM, 2007.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © A.N. Sychev, 2012, published in Avtomatika i Vychislitel’naya Tekhnika, 2012, No. 6, pp. 17–32.
About this article
Cite this article
Sychev, A.N. Composition of logical switching networks in neural structures. Aut. Control Comp. Sci. 46, 248–260 (2012). https://doi.org/10.3103/S0146411612060089
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411612060089