Result: On the use of multiplicative neuron in feedforward neural networks
Title:
On the use of multiplicative neuron in feedforward neural networks
Authors:
Source:
International journal of modelling & simulation. 26(4):331-336
Publisher Information:
Anaheim, CA; Calgary, AB; Zürich: Acta Press, 2006.
Publication Year:
2006
Physical Description:
print, 20 ref
Original Material:
INIST-CNRS
Subject Terms:
Electronics, Electronique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Connexionnisme. Réseaux neuronaux, Connectionism. Neural networks, Electronique, Electronics, Circuits électriques, optiques et optoélectroniques, Electric, optical and optoelectronic circuits, Réseaux neuronaux, Neural networks, Algorithme rétropropagation, Backpropagation algorithm, Algoritmo retropropagación, Apprentissage, Learning, Aprendizaje, Approximation fonction, Function approximation, Décomposition fonction, Function decomposition, Descomposición función, Essai fonctionnel, Functional test, Prueba funcional, Générateur fonction, Function generator, Generador función, Mappage, Mapping, Carta de datos, Modèle mathématique, Mathematical model, Modelo matemático, Modélisation, Modeling, Modelización, Multiplication, Multiplicación, Réseau multicouche, Multilayer network, Red multinivel, Réseau neuronal non bouclé, Feedforward neural nets, Réseau neuronal, Neural network, Red neuronal, Simulation système, System simulation, Simulación sistema, Série temporelle, Time series, Serie temporal, Multiplicative neuron model, backpropagation algorithm, feedforward neural networks, function approximation, time series prediction
Document Type:
Academic journal
Article
File Description:
text
Language:
English
Author Affiliations:
Department of Electronics, M.A. National Institute of Technolog, Bhopal, India
Department of Electrical Engineering, Indian Institute of Technology, Kanpur, India
Department of Electrical Engineering, Indian Institute of Technology, Kanpur, India
ISSN:
0228-6203
Rights:
Copyright 2007 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Computer science; theoretical automation; systems
Electronics
Electronics
Accession Number:
edscal.18458434
Database:
PASCAL Archive
Further Information
Neurons are functional units and can be considered as generators of function spaces. Neuron modelling concerns relating the function to the structure of the neuron on the basis of its operation. Most existing neuron models are based on the summing operation of the inputs. In this paper we present a new neuron model, multiplicative neuron, that performs multiplication operation instead of simple summation. The computational and learning capabilities of the model have been tested on some functional mapping and time series prediction problems. Simulation results show that the proposed neuron model, when used in a feedforward neural network, performs better than existing multilayer networks (MLN).