Solving hard local minima problems using basin cells for multilayer perceptron training

Authors:
Younggui Yoon;Jaewook Lee
Affiliations:
Department of Physics, Chung-Ang University, Seoul, Korea;Department of Industrial and Management Engineering, Pohang University of Science and Technology, Pohang, Kyungbuk, Korea
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Year:
2005

Citing 2
Cited 0

First- and second-order methods for learning: between steepest descent and Newton's method

Neural Computation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation

Quantified Score

Hi-index	0.00

Visualization

Abstract

An analysis of basin cells for an error surface of an multilayer perceptron is presented. Utilizing the topological structure of the basin cells, an escaping strategy is proposed to solve difficult local minima problems. A numerical example is given to illustrate the proposed method and is shown to have a potential to locate better local minima efficiently.