Gradient descent decomposition for multi-objective learning

Authors:
Marcelo Azevedo Costa;Antônio Pádua Braga
Affiliations:
Universidade Federal de Minas Gerais, Departament of Statistics and Department of Electronics, Belo Horizonte, Minas Gerais, Brazil;Universidade Federal de Minas Gerais, Departament of Statistics and Department of Electronics, Belo Horizonte, Minas Gerais, Brazil
Venue:
IDEAL'11 Proceedings of the 12th international conference on Intelligent data engineering and automated learning
Year:
2011

Citing 5
Cited 0

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory

The nature of statistical learning theory
Improving generalization of MLPs with sliding mode control and the Levenberg-Marquardt algorithm

Neurocomputing
A multi-objective approach to RBF network learning

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

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multi-objective learning has been explored in neural network because it adjusts the model capacity providing better generalization properties. It usually requires sophisticated algorithms such as ellipsoidal, sliding-mode, genetic algorithms, among others. This paper proposes an affordable algorithm that decomposes the gradient into two components and it adjusts the weights of the network separately. By doing so multi-objective learning with L2 norm control is accomplished.