A novel hybrid neural learning algorithm using simulated annealing and quasisecant method

Authors:
John Yearwood;Adil Bagirov;Sattar Seifollahi
Affiliations:
University of Ballarat, Victoria, Australia;University of Ballarat, Victoria, Australia;University of Ballarat, Victoria, Australia and University of Adelaide, South Australia, Australia
Venue:
AusDM '11 Proceedings of the Ninth Australasian Data Mining Conference - Volume 121
Year:
2011

Citing 11
Cited 0

Advanced algorithms for neural networks: a C++ sourcebook

Advanced algorithms for neural networks: a C++ sourcebook
Regularization theory and neural networks architectures

Neural Computation
Pattern recognition using neural networks: theory and algorithms for engineers and scientists

Pattern recognition using neural networks: theory and algorithms for engineers and scientists
A bundle-Newton method for nonsmooth unconstrained minimization

Mathematical Programming: Series A and B
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Generalized Bundle Methods

SIAM Journal on Optimization
Semi-supervised Learning of Tree-Structured RBF Networks Using Co-training

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Attribute weighting via genetic algorithms for attribute weighted artificial immune system (AWAIS) and its application to heart disease and liver disorders problems

Expert Systems with Applications: An International Journal
Solving a system of nonlinear integral equations by an RBF network

Computers & Mathematics with Applications
A quasisecant method for minimizing nonsmooth functions

Optimization Methods & Software - DEDICATED TO PROFESSOR VLADIMIR F. DEMYANOV ON THE OCCASION OF HIS 70TH BIRTHDAY

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a hybrid learning algorithm for the single hidden layer feedforward neural networks (SLFNs) for data classification. The proposed hybrid algorithm is a two-phase learning algorithm and is based on the quasisecant and the simulated annealing methods. First, the weights between the hidden layer and the output layer nodes (output layer weights) are adjusted by the quasisecant algorithm. Then the simulated annealing is applied for global attribute weighting. The weights between the input layer and the hidden layer nodes are fixed in advance and are not included in the learning process. The proposed two-phase learning of the network is a novel idea and is different from that of the existing ones. The numerical results on some benchmark data sets are also reported and these results are promising.