Logo

Sequential Learning Methods on RBF with Novel Approach of Minimal Weight Update

Asirvadam , Vijanth Sagayan and McLoone, Sean (2006) Sequential Learning Methods on RBF with Novel Approach of Minimal Weight Update. In: IEEE Nonlinear Statistical Signal Processing Workshop, 2006, 13-15 September 2006, Cambridge UK.

Full text not available from this repository.

Official URL: http://ieeexplore.ieee.org/Xplore/login.jsp?url=ht...

Abstract

This paper investigates sequential learning method with new form of weight update applied on a decomposed form of training algorithms using Radial Basis Function (RBF) network. Adding each basis function to the hidden layer during the course of training facilitate the weight update to be decomposed on neuron by neuron basis. A new form weight update is introduced where the weight update is based on minimal displacement of the current input elements to the elements of the nearest centre of the Gaussian neuron.

Item Type:Conference or Workshop Item (Paper)
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
Departments / MOR / COE:Departments > Electrical & Electronic Engineering
ID Code:3985
Deposited By: Dr Vijanth Sagayan Asirvadam
Deposited On:13 Jan 2011 05:00
Last Modified:13 Jan 2011 05:00

Repository Staff Only: item control page