A New Learning Algorithm Using Simultaneous Perturbation with Weight Initialization

Authors:
T. Kathirvalavakumar;P. Thangavel
Affiliations:
Department of Computer Science, V.H.N.S.N. College, Virudhunagar;Department of Computer Science, University of Madras, Chepauk, Chennai-600 005, India. e-mail: thangavelp@yahoo.com
Venue:
Neural Processing Letters
Year:
2003

Citing 9
Cited 2

Asymptotic global behavior for stochastic approximation and diffusions with slowly decreasing noise effects: Global minimization via Monte Carlo

SIAM Journal on Applied Mathematics
On Langevin updating in multilayer perceptrons

Neural Computation
A sequential learning approach for single hidden layer neural networks

Neural Networks
Accelerating neural network training using weight extrapolations

Neural Networks
The cascade-correlation learning: a projection pursuit learning perspective

IEEE Transactions on Neural Networks
Learning rules for neuro-controller via simultaneous perturbation

IEEE Transactions on Neural Networks
Objective functions for training new hidden units in constructive neural networks

IEEE Transactions on Neural Networks
Dynamic tunneling technique for efficient training of multilayer perceptrons

IEEE Transactions on Neural Networks
Fast initialization for cascade-correlation learning

IEEE Transactions on Neural Networks

A Modified Backpropagation Training Algorithm for Feedforward Neural Networks

Neural Processing Letters
An improved three-term optical backpropagation algorithm

International Journal of Artificial Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new learning algorithm is proposed for training single hidden layer feedforward neural network. In each epoch, the connection weights are updated by simultaneous perturbation. Tunneling using perturbation technique is applied to detrap the local minima. The proposed technique is shown to give better convergence results for the selected problems, namely neuro-controller, XOR, L-T character recognition, two spirals, simple interaction function, harmonic function and complicated interaction function.