Improvements to the conventional layer-by-layer BP algorithm
Publication in refereed journal


Full Text

Times Cited
Web of Science0WOS source URL (as at 14/09/2020) Click here for the latest count

Other information
AbstractThis paper points out some drawbacks and proposes some modifications to the conventional layer-by-layer BP algorithm. In particular, we present a new perspective to the learning rate, which is to use a heuristic rule to define the learning rate so as to update the weights. Meanwhile, to pull the algorithm out of saturation area and prevent it from converging to a local minimum, a momentum term is introduced to the former algorithm. And finally the effectiveness and efficiency of the proposed method are demonstrated by two benchmark examples.
All Author(s) ListLi XQ, Han F, Lok TM, Lyu MR, Huang GB
Name of ConferenceInternational Conference on Intelligent Computing
Start Date of Conference23/08/2005
End Date of Conference26/08/2005
Place of ConferenceHefei
Journal nameLecture Notes in Artificial Intelligence
Detailed descriptionorganized by Institute of Intelligent Machines, and the University of Science & Technology of China, Chinese Academy of Sciences ,\n\nTo ORKTS: indexe
Year2005
Month1
Day1
Volume Number3645
PublisherSPRINGER-VERLAG BERLIN
Pages189 - 198
ISBN3-540-28227-0
ISSN0302-9743
LanguagesEnglish-United Kingdom
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; Computer Science, Theory & Methods

Last updated on 2020-15-09 at 02:49