Single multiplicative neuron model based on generalized mean

Author

Attia, M.A. ; Sallam, Elsayed A. ; Fahmy, M.M.

Author_Institution

Dept. of Comput. & Autom. Control, Tanta Univ., Tanta, Egypt

fYear

2012

fDate

27-29 Nov. 2012

Firstpage

111

Lastpage

116

Abstract

This paper presents a single multiplicative neuron model based on a polynomial architecture. The proposed neuron model consists of a non-linear aggregation function based on the concept of generalized mean of all multiplicative inputs. This neuron model has the same number of parameters as the single multiplicative neuron model (SMN). The SMN model is a special case of the proposed generalized mean single multiplicative neuron (GMSMN) model. The structure of this model is simpler than higher-order neuron model. The simulation results show that the performance of the proposed neuron model is better than SMN model.

Keywords

neural nets; polynomials; statistical analysis; GMSMN model; SMN model; generalized mean concept; generalized mean single multiplicative neuron model; higher-order neuron model; multiplicative input; nonlinear aggregation function; polynomial architecture; single multiplicative neuron model; Computational modeling; Mathematical model; Neurons; Predictive models; Testing; Time series analysis; Training; Classification; Geometric Mean; Single Multiplicative Neuron Model; Time Series Prediction; generalized mean;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Engineering & Systems (ICCES), 2012 Seventh International Conference on

Conference_Location

Cairo

Print_ISBN

978-1-4673-2960-6

Type

conf

DOI

10.1109/ICCES.2012.6408495

Filename

6408495