The usage of golden section in calculating the efficient solution in artificial neural networks training by multi-objective optimization

Authors:
Roselito A. Teixeira;Antônio P. Braga;Rodney R. Saldanha;Ricardo H. C. Takahashi;Talles H. Medeiros
Affiliations:
Centro Universitário do Leste de Minas Gerais, Coronel Fabriciano, MG, Brazil;Federal University of Minas Gerais, Department of Electronic Engineering, Belo Horizonte, MG, Brazil;Federal University of Minas Gerais, Department of Electrical Engineering, Belo Horizonte, MG, Brazil;Federal University of Minas Gerais, Department of Mathematics, Belo Horizonte, MG, Brazil;Federal University of Minas Gerais, Department of Electronic Engineering, Belo Horizonte, MG, Brazil
Venue:
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Year:
2007

Citing 3
Cited 2

Deterministic Boltzmann learning performs steepest descent in weight-space

Neural Computation
Neural networks and the bias/variance dilemma

Neural Computation
Regularization theory and neural networks architectures

Neural Computation

Gradient descent decomposition for multi-objective learning

IDEAL'11 Proceedings of the 12th international conference on Intelligent data engineering and automated learning
A computational geometry approach for pareto-optimal selection of neural networks

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work a modification was made on the algorithm of Artificial Neural Networks (NN) Training of the Multilayer Perceptron type (MLP) based on multi-objective optimization (MOBJ), to increase its computational efficiency. Usually, the number of efficient solutions to be generated is a parameter that must be provided by the user. In this work, this number is automatically determined by an algorithm, through the usage of golden section, being generally less when specified, showing a sensible reduction in the processing time and keeping the high generalization capability of the obtained solution from the original method.