Abstract
A new class of the artificial neuron models is described in this work. These models are based on assumptions: (1) contributions of synapses are summing with the help of certain aggregation operation; (2) contribution of synaptic clusters are computed with the help of another aggregation operation on the set of simple synapses. These models include a big part of known functional models of neurons. The generalization of the \(\varSigma \varPi \)-neuron model on the basis of aggregation operations is presented. Correctness of the \(\varSigma \varPi \)-neuron model of aggregating type under easily verifiable conditions is also presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mesiar, R., Komornikova, M., Kolesarova, A., Calvo, T.: Aggregation functions: A revision. In: Bustince, H., Herrera, F., Montero, J. (eds.) Fuzzy Sets and Their Extensions: Representation. Aggregation and Models. Springer, Berlin (2008)
Grabich, M., Marichal, J.-L., Pap, E.: Aggregation Functions. Series: Encyclopedia of Mathematics and its Applications. Cambridge University Press, New York (2009)
Pap, E.: \(g\)-calculus. Univ. u Novom Sadu Zb. Rad. Prirod.-Mat. Fak. Ser. Mat. 23, 145–150 (1993)
Pap, E.: Preprint ESI 1448. Vienna 23, 145–156 (2004)
Aczél, J.: Lectures on Functional Equations and their Applications. Academic Press, New York (1966)
Feldman, J.A., Ballard, D.H.: Connectionist models and their properties. Cogn. Sci. 6, 205–254 (1982)
Rumelhart, D.E., Hinton, G., Williams, R.: Learning internal representation by error propagation. Parallel Distrib. Process. 1, 318–362 (1986)
Mel, B.W.: The Sigma-Pi Column: A Model of Associative Learning in Cerebral Neocortex. California institute of technology. cns memo no. 6: Technical report Pasadena, California 91125 (1990)
Mel, B.W.: The Sigma-Pi model neuron: roles of the dendritic tree in associative learning. Soc. NeuroSci. Abstr. 16, 205 (1990)
Mel, B.W., Koch, C.: Sigma-Pi learning: on radial basis functions and cortical associative learning. In: Touretzk, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 2, pp. 474–481. Morgan Kaufmann, San Mateo, CA (2000)
Mel, B.W.: Why have dendrites? a computational perspective. In: Stuart, G., Spruston, N., Hausse, M. (eds.) Dendrites 2nd edn, Oxford University Press (2007)
Sibzukhov, Z.M.: Constructive Learning Methods of \(\varSigma \varPi \)-Neural Networks. - M: Nauka. (in Russian) (2006)
Shibzukhov, Z.M., Cherednikov, D.: About neuron models of aggregating types. Mach. Learn. Data Anal. 1, 1706–1716 (2015). http://jmlda.org/?page_id=35 (in Russian)
Shibzukhov, Z.M.: Recurrent method of constructive learning of some networks \(\varSigma \varPi \)-Neurons and \(\varSigma \varPi \) neural modules. J. Comput. Math. Math. Phisycs. 43, 1298–1310 (2003)
Shibzukhov, Z.M.: On constructive and well-behaved classes of algebraic \(\varSigma \varPi \)-algorithms. Doklady Math. 81, 490–492 (2010)
Acknowledgements
This work is supported by grant RFBR 15-01-03381 and by research program of ONIT RAS.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Shibzukhov, Z., Cherednikov, D. (2016). About \(\varSigma \varPi \)-neuron Models of Aggregating Type. In: Cheng, L., Liu, Q., Ronzhin, A. (eds) Advances in Neural Networks – ISNN 2016. ISNN 2016. Lecture Notes in Computer Science(), vol 9719. Springer, Cham. https://doi.org/10.1007/978-3-319-40663-3_75
Download citation
DOI: https://doi.org/10.1007/978-3-319-40663-3_75
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-40662-6
Online ISBN: 978-3-319-40663-3
eBook Packages: Computer ScienceComputer Science (R0)