Development and convergence analysis of training algorithms with local learning rate adaptation

G.D. Magoulas, V.P. Plagianakos, M.N. Vrahatis
2000 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium  
Abstract| A new theorem for the development and convergence analysis of supervised training algorithms with an adaptive learning rate for each weight is presented. Based on this theoretical result, a strategy is proposed to automatically adapt the search direction, as well as the stepsize length along the resultant search direction. This strategy is applied to some well known local learning algorithms to investigate its e ectiveness.
doi:10.1109/ijcnn.2000.857808 dblp:conf/ijcnn/MagoulasPV00 fatcat:bifbxddifrdh3acc2d2t5h3ppu