Supervised Learning with Generalization as an Inverse Problem
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F05%3A00405483" target="_blank" >RIV/67985807:_____/05:00405483 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Supervised Learning with Generalization as an Inverse Problem
Original language description
Capability of generalization in learning of neural networks from examples can be modelled using regularization, which has been developed as a tool for improving stability of solutions of inverse problems. Such problems are typically described by integraloperators. It is shown that learning from examples can be reformulated as an inverse problem defined by an evaluation operator. This reformulation leads to an analytical description of an optimal input/output function of a network with kernel units, which can be employed to design a learning algorithm based on a numerical solution of a system of linear equations.
Czech name
Učení neuronových sítí jako inverzní úloha
Czech description
Schopnost učení neuronových sítí na základě příkladů může být modelována pomocí regularizace, která byla vyvinuta jako nástroj pro zlepšení stability řešení inverzních úloh.
Classification
Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
BA - General mathematics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/1ET100300517" target="_blank" >1ET100300517: Methods for Intelligent Systems and Their Applications in Datamining and Natural Language Processing</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2005
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Interest Group in Pure and Applied Logics. Logic Journal
ISSN
1367-0751
e-ISSN
—
Volume of the periodical
13
Issue of the periodical within the volume
-
Country of publishing house
GB - UNITED KINGDOM
Number of pages
8
Pages from-to
551-559
UT code for WoS article
—
EID of the result in the Scopus database
—