| Convergence of cyclic and almost-cyclic learning with momentum for feedforward neural networks. | |
| | |
MedLine Citation:
|
PMID: 21813357 Owner: NLM Status: In-Data-Review |
Abstract/OtherAbstract:
|
Two backpropagation algorithms with momentum for feedforward neural networks with a single hidden layer are considered. It is assumed that the training samples are supplied to the network in a cyclic or an almost-cyclic fashion in the learning procedure, i.e., in each training cycle, each sample of the training set is supplied in a fixed or a stochastic order respectively to the network exactly once. A restart strategy for the momentum is adopted such that the momentum coefficient is set to zero at the beginning of each training cycle. Corresponding weak and strong convergence results are then proved, indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point, respectively. The convergence conditions on the learning rate, the momentum coefficient, and the activation functions are much relaxed compared with those of the existing results. |
| | |
Authors:
|
Jian Wang; Jie Yang; Wei Wu |
Related Documents
:
|
22033537 - Principles of sensorimotor learning. 11590777 - More patients seek drugs through adaps, creating $50 million deficit. 10558477 - Notice of availability of funding for alternative projects, known as wilson/fish projec... 2942477 - Poverty and social welfare: an agenda for change. 12870407 - Student impairment and remediation in accredited marriage and family therapy programs. 1126767 - Altering the gambler's maladaptive life goals. |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council Volume: 22 ISSN: 1941-0093 ISO Abbreviation: IEEE Trans Neural Netw Publication Date: 2011 Aug |
Date Detail:
|
Created Date: 2011-08-04 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 101211035 Medline TA: IEEE Trans Neural Netw Country: United States |
Other Details:
|
Languages: eng Pagination: 1297-306 Citation Subset: IM |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Rapid Detection of Small Oscillation Faults via Deterministic Learning.
Next Document: l(p)-l(q) Penalty for Sparse Linear and Sparse Multiple Kernel Multitask Learning.