A linear learning method for multilayer perceptrons using least-squares

Authors:
Bertha Guijarro-Berdiñas;Oscar Fontenla-Romero;Beatriz Pérez-Sánchez;Paula Fraguela
Affiliations:
Department of Computer Science, Facultad de Informática, Universidad de A Coruña, A Coruña, Spain;Department of Computer Science, Facultad de Informática, Universidad de A Coruña, A Coruña, Spain;Department of Computer Science, Facultad de Informática, Universidad de A Coruña, A Coruña, Spain;Department of Computer Science, Facultad de Informática, Universidad de A Coruña, A Coruña, Spain
Venue:
IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning
Year:
2007

Citing 6
Cited 5

Original Contribution: A learning algorithm for multilayered neural networks based on linear least squares problems

Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
A global optimum approach for one-layer neural networks

Neural Computation
Effiicient BackProp

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop
Linear least-squares based methods for neural networks learning

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Linear-least-squares initialization of multilayer perceptrons through backpropagation of the desired response

IEEE Transactions on Neural Networks

New Artificial Metaplasticity MLP Results on Standard Data Base

IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part I: Bio-Inspired Systems: Computational and Ambient Intelligence
Breast Cancer Classification Applying Artificial Metaplasticity

IWINAC '09 Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation: Part II: Bioinspired Applications in Artificial and Natural Computation
Breast cancer classification applying artificial metaplasticity algorithm

Neurocomputing
WBCD breast cancer database classification applying artificial metaplasticity neural network

Expert Systems with Applications: An International Journal
Cartesian genetic programming encoded artificial neural networks: a comparison using three benchmarks

Proceedings of the 15th annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Training multilayer neural networks is typically carried out using gradient descent techniques. Ever since the brilliant backpropagation (BP), the first gradient-based algorithm proposed by Rumelhart et al., novel training algorithms have appeared to become better several facets of the learning process for feed-forward neural networks. Learning speed is one of these. In this paper, a learning algorithm that applies linear-least-squares is presented. We offer the theoretical basis for the method and its performance is illustrated by its application to several examples in which it is compared with other learning algorithms and well known data sets. Results show that the new algorithm upgrades the learning speed of several backpropagation algorithms, while preserving good optimization accuracy. Due to its performance and low computational cost it is an interesting alternative, even for second order methods, particularly when dealing large networks and training sets.