Separable recursive training algorithms for feedforward neural networks

• Main Authors: Asirvadam , Vijanth Sagayan, McLoone, Sean, Irwin, George W
• Format: Conference or Workshop Item
• Published: 2002
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1007667; http://eprints.utp.edu.my/3957/

Novel separable recursive training strategies are derived for the training of feedforward neural networks. These hybrid algorithms combine nonlinear recursive optimization of hidden-layer nonlinear weights with recursive least-squares optimization of linear output-layer weights in one integrated rou...