Result: A Hierarchical Genetic Algorithm Coding for Constructing and Learning an Optimal Neural Network

Title:
A Hierarchical Genetic Algorithm Coding for Constructing and Learning an Optimal Neural Network
Authors:
IMEN BEN OMRANE, CHATTI, A
Source:
Nonlinear dynamics and systems theory. 10(3):269-282
Publisher Information:
Kiev: Informath Publishing Group, 2010.
Publication Year:
2010
Physical Description:
print, 16 ref
Original Material:
INIST-CNRS
Subject Terms:
Control theory, operational research, Automatique, recherche opérationnelle, Mathematics, Mathématiques, Mechanics acoustics, Mécanique et acoustique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Informatique théorique, Theoretical computing, Algorithmique. Calculabilité. Arithmétique ordinateur, Algorithmics. Computability. Computer arithmetics, Intelligence artificielle, Artificial intelligence, Connexionnisme. Réseaux neuronaux, Connectionism. Neural networks, Algorithme génétique, Genetic algorithm, Algoritmo genético, Algorithme rétropropagation, Backpropagation algorithm, Algoritmo retropropagación, Optimisation, Optimization, Optimización, Optimum local, Local optimum, Optimo local, Réseau neuronal, Neural network, Red neuronal, Résolution problème, Problem solving, Resolución problema, Rétropropagation, Backpropagation, Retropropagacíon, Solution globale, Global solution, Solución global, Solution optimale, Optimal solution, Solución óptima, Perceptron multicouche, Multilayer perceptrons, Perceptrón multicapa, 92B20, 93A13, backpropagation algorithm, hierarchical genetic algorithms, learning, multilayer perceptron, neural networks, optimization
Document Type:
Academic journal Article
File Description:
text
Language:
English
Author Affiliations:
Institut National des Sciences Appliquees et de Technologie INSAT, Centre Urbain Nord BP 676, 1080 Tunis, Tunisia
ISSN:
1562-8353
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=23183042
Rights:
Copyright 2015 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
Accession Number:
edscal.23183042
Database:
PASCAL Archive

Further Information

Neural Networks (NN) proved to be a powerful problem solving mechanism with great ability to learn. The success and speed of training is based on the initial parameter settings such as architecture, initial weights, learning rates and others. The most used method of training Neuron Networks is the back propagation of the gradient. Although this method provides a global optimal solution in a reasonable time, it can converge towards local minimum, in addition to large number of parameters that should be fixed previously. Within this framework of study, we propose a new coding for a hierarchical genetic algorithm for the determination of the structure and the training of the Neuron Networks. These algorithms are known for structures' an parameters' optimization. We will prove that Hierarchical genetic algorithm can improve the result of backpropagation of gradient.