Number of the records: 1
Neural Network Learning as an Inverse Problem
- 1.0405483 - UIVT-O 330858 RIV GB eng J - Journal Article
Kůrková, Věra
Neural Network Learning as an Inverse Problem.
[Učení neuronových sítí jako inverzní úloha.]
Logic Journal of the IGPL. Roč. 13, č. 5 (2005), s. 551-559. ISSN 1367-0751. E-ISSN 1368-9894
R&D Projects: GA AV ČR 1ET100300517
Institutional research plan: CEZ:AV0Z10300504
Keywords : learning from data * generalization * empirical error functional * inverse problem * evaluation operator * kernel methods
Subject RIV: BA - General Mathematics
Impact factor: 0.382, year: 2005
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 integral operators. 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.
Schopnost učení neuronových sítí na základě příkladů může být modelována pomocí regularizace, která byla vyvinuta jako nástroj pro zlepšení stability řešení inverzních úloh.
Permanent Link: http://hdl.handle.net/11104/0125645
Number of the records: 1