Fast sequential learning methods on RBF-network using decomposed training algorithms

• Main Authors: Asirvadam , Vijanth Sagayan, McLoone, Sean, Irwin, George W
• Format: Conference or Workshop Item
• Published: 2004
• Subjects: TK Electrical engineering. Electronics Nuclear engineering; QA75 Electronic computers. Computer science
• Online Access: http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1387663; http://eprints.utp.edu.my/4028/

This work investigates novel sequential learning methods applied on a decomposed form of training algorithms using radial basis function (RBF) network. The dynamic expansion of RBF network by adding neurons to the hidden layer during the course of training facilitates the weight update to be decompo...