AN ADAPTIVE TRAINING ALGORITHM FOR BACKPROPAGATION NEURAL NETWORKS

Authors
HSIN HC LI CC SUN MG SCLABASSI RJ
Citation
Hc. Hsin et al., AN ADAPTIVE TRAINING ALGORITHM FOR BACKPROPAGATION NEURAL NETWORKS, IEEE transactions on systems, man, and cybernetics, 25(3), 1995, pp. 512-514
Citations number
16
Categorie Soggetti
Controlo Theory & Cybernetics","Computer Science Cybernetics","Engineering, Eletrical & Electronic
Journal title
IEEE transactions on systems, man, and cybernetics → ACNP
ISSN journal
00189472
Volume
25
Issue
3
Year of publication
1995
Pages
512 - 514
Database
ISI
SICI code
0018-9472(1995)25:3<512:AATAFB>2.0.ZU;2-M
Abstract
A dynamic learning rate for back-propagation training of artificial ne ural networks is proposed as a weighted average of direction cosines o f the incremental weight vectors of the current and previous steps. Ex periments on training an EEG-based sleep state pattern recognition sch eme have demonstrated its improved performance.