| Learning algorithms for feedforward networks based on finite samples. | |
| | |
MedLine Citation:
|
PMID: 18263488 Owner: NLM Status: In-Data-Review |
Abstract/OtherAbstract:
|
We present two classes of convergent algorithms for learning continuous functions and regressions that are approximated by feedforward networks. The first class of algorithms, applicable to networks with unknown weights located only in the output layer, is obtained by utilizing the potential function methods of Aizerman et al. (1970). The second class, applicable to general feedforward networks, is obtained by utilizing the classical Robbins-Monro style stochastic approximation methods (1951). Conditions relating the sample sizes to the error bounds are derived for both classes of algorithms using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can be directly adapted to concept learning problems. |
| | |
Authors:
|
N V Rao; V Protopopescu; R C Mann; E M Oblow; S S Iyengar |
Related Documents
:
|
17454408 - Modified adaptive resonance theory based control strategy for emg operated prosthesis f... 18244378 - Independent component analysis using potts models. 18252488 - Existence, learning, and replication of periodic motions in recurrent neural networks. 7941388 - Integration of shading and texture cues: testing the linear model. 20182008 - Empirical study of unipolar and bipolar configurations using high resolution single mul... 16253008 - Steady dark solitary waves emerging from wave-generated meanflow: the role of modulatio... |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council Volume: 7 ISSN: 1045-9227 ISO Abbreviation: IEEE Trans Neural Netw Publication Date: 1996 |
Date Detail:
|
Created Date: 2008-02-11 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: 926-40 Citation Subset: - |
Affiliation:
|
Center for Eng. Syst. Adv. Res., Oak Ridge Nat. Lab., TN. |
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: A theoretical comparison of batch-mode, on-line, cyclic, and almost-cyclic learning.
Next Document: Progressive learning and its application to robot impedance learning.