An improved training algorithm for feedforward neural network learning based on terminal attractors

Authors:
Xinghuo Yu;Bin Wang;Batsukh Batbayar;Liuping Wang;Zhihong Man
Affiliations:
Platform Technologies Research Institute, RMIT University, Melbourne, Australia 3001 and School of Automation, Southeast University, Nanjing, China;School of Electrical and Computer Engineering, RMIT University, Melbourne, Australia 3001;School of Information Technology, National University of Mongolia, Ulaanbaatar, Mongolia;School of Electrical and Computer Engineering, RMIT University, Melbourne, Australia 3001;Faculty of Engineering and Industrial Sciences, Swinburne University of Technology, Melbourne, Australia 3122
Venue:
Journal of Global Optimization
Year:
2011

Citing 10
Cited 1

Terminal attractors in neural networks

Neural Networks
Introduction to artificial neural systems

Introduction to artificial neural systems
Neural Network Time Series Forecasting of Financial Markets

Neural Network Time Series Forecasting of Financial Markets
Artificial Neural Networks: Concepts and Theory

Artificial Neural Networks: Concepts and Theory
A Modified Backpropagation Training Algorithm for Feedforward Neural Networks

Neural Processing Letters
Development and Evaluation of Decision-Making Model for Stock Markets

Journal of Global Optimization
A generalized learning paradigm exploiting the structure of feedforward neural networks

IEEE Transactions on Neural Networks
Advanced neural-network training algorithm with reduced complexity based on Jacobian deficiency

IEEE Transactions on Neural Networks
A fast feedforward training algorithm using a modified form of the standard backpropagation algorithm

IEEE Transactions on Neural Networks
A general backpropagation algorithm for feedforward neural networks learning

IEEE Transactions on Neural Networks

Fixed point method for autonomous on-line neural network training

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an improved training algorithm based on the terminal attractor concept for feedforward neural network learning is proposed. A condition to avoid the singularity problem is proposed. The effectiveness of the proposed algorithm is evaluated by various simulation results for a function approximation problem and a stock market index prediction problem. It is shown that the terminal attractor based training algorithm performs consistently in comparison with other existing training algorithms.