Adaptive basis function for artificial neural networks

Ninan Sajeeth Philip

doi:10.1016/S0925-2312(01)00578-1

Return

Adaptive basis function for artificial neural networks

2002-08-01

PRE

Ninan Sajeeth Philip *

K Babu Joseph

DOI：10.1016/S0925-2312(01)00578-1

Original

Original request for help

Save

Abstract

En 中文

It is shown that modifying the sigmoidal basis function of a multi-layer feedforward artificial neural network using a control parameter improves the network's ability to learn. The modification is rendered by a gradient descent algorithm similar to the back-propagation. In doing so, the method retains all the goodies of the sigmoidal function and causes the ANN to approximate the decision function faster and also with better accuracy. (C) 2002 Elsevier Science B.V. All rights reserved.

Keywords:

back propagation algorithm

neural networks

optimization of basis function