| A new approach to perceptron training. | |
| | |
MedLine Citation:
|
PMID: 18238004 Owner: NLM Status: In-Data-Review |
Abstract/OtherAbstract:
|
The training of perceptrons is discussed in the framework of nonsmooth optimization. An investigation of Rosenblatt's perceptron training rule shows that convergence or the failure to converge in certain situations can be easily understood in this framework. An algorithm based on results from nonsmooth optimization is proposed and its relation to the "constrained steepest descent" method is investigated. Numerical experiments verify that the "constrained steepest descent" algorithm may be further improved by the integration of methods from nonsmooth optimization. |
| | |
Authors:
|
C Eitzinger; H Plach |
Related Documents
:
|
16375794 - Telemedicine by email in remote cambodia. 12453354 - Estimated costs of false laboratory diagnoses of tuberculosis in three patients. 10363204 - Laboratory role in the management of hospital acquired infections. 7361814 - An evaluation of the j. t. baker 700 and the royco cell-crit iv. 18186974 - Safety and effectiveness of amphotericin b deoxycholate for the treatment of visceral l... 21452424 - Land grab. more investors offer hospitals cash for their real estate as providers hunt ... |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council Volume: 14 ISSN: 1045-9227 ISO Abbreviation: IEEE Trans Neural Netw Publication Date: 2003 |
Date Detail:
|
Created Date: 2008-02-01 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: 216-21 Citation Subset: - |
Affiliation:
|
Protactor Res., Steyr, Austria. |
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: Content-based audio classification and retrieval by support vector machines.
Next Document: Asymptotic stability criteria for a two-neuron network with different time delays.