Journal
NEUROCOMPUTING
Volume 64, Issue -, Pages 253-270Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2004.11.016
Keywords
supervised learning; batch learning; first-order training algorithms; convergence analysis; global convergence property; Rprop; IRprop
Categories
Ask authors/readers for more resources
In this paper, a new globally convergent modification of the Resilient Propagation-Rprop algorithm is presented. This new addition to the Rprop family of methods builds on a mathematical framework for the convergence analysis that ensures that the adaptive local learning rates of the Rprop's schedule generate a descent search direction at each iteration. Simulation results in six problems of the PROBEN1 benchmark collection show that the globally convergent modification of the Rprop algorithm exhibits improved learning speed, and compares favorably against the original Rprop and the Improved Rprop, a recently proposed Rrpop modification. (c) 2004 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available