Direct search as unsupervised training algorithm for neural networks

Authors:
Cătălin-Daniel Căleanu;Xia Mao;Vigil Tiponuţ;Yuli Xue
Affiliations:
Applied Electronics Department, University;School of Electronic and Information Engineering, Beihang University, Beijing, Beijing, China;Applied Electronics Department, University;School of Electronic and Information Engineering, Beihang University, Beijing, Beijing, China
Venue:
ICS'10 Proceedings of the 14th WSEAS international conference on Systems: part of the 14th WSEAS CSCC multiconference - Volume II
Year:
2010

Citing 12
Cited 0

On the Convergence of Pattern Search Algorithms

SIAM Journal on Optimization
Pattern Search Algorithms for Bound Constrained Minimization

SIAM Journal on Optimization
Analysis of Generalized Pattern Searches

SIAM Journal on Optimization
A Hybrid Training Algorithm for Feedforward Neural Networks

Neural Processing Letters
Nonsmooth optimization through Mesh Adaptive Direct Search and Variable Neighborhood Search

Journal of Global Optimization
Pattern classification with class probability output network

IEEE Transactions on Neural Networks
Novel maximum-margin training algorithms for supervised neural networks

IEEE Transactions on Neural Networks
Fast training of multilayer perceptrons

IEEE Transactions on Neural Networks
Tuning of the structure and parameters of a neural network using an improved genetic algorithm

IEEE Transactions on Neural Networks
Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm

IEEE Transactions on Neural Networks
An Optimization Methodology for Neural Network Weights and Architectures

IEEE Transactions on Neural Networks
The Hierarchical Fast Learning Artificial Neural Network (HieFLANN)—An Autonomous Platform for Hierarchical Neural Network Construction

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel unsupervised training method, based on direct search optimization technique, which could be successfully employed in the finding the optimal free parameters, e.g. weights and biases, of an artificial neural network (ANN). Benchmark data sets of artificial and real-world problems have been used in experiments that enable a comparison with other optimization methods e.g. genetic algorithm and state-of-the-art classifiers. The results provide evidence of the effectiveness of our method regarding the possibility of finding the optimal values of weights and biases of a multilayer perceptron neural network and constructing an ANN autonomously.