Počet záznamů: 1
Variants of Learning Algorithm Based on Kolmogorov Theorem
- 1.0404626 - UIVT-O 20020038 RIV NL eng C - Konferenční příspěvek (zahraniční konf.)
Neruda, Roman - Štědrý, Arnošt - Drkošová, Jitka
Variants of Learning Algorithm Based on Kolmogorov Theorem.
Computational Science. Vol. 3. Berlin: Springer, 2002 - (Sloot, P.; Tan, C.; Dongarra, J.; Hoekstra, A.), s. 536-543. Lecture Notes in Computer Science, 2331. ISBN 3-540-43594-8. ISSN 0302-9743.
[ICCS 2002. International Conference. Amsterdam (NL), 21.04.2002-24.04.2002]
Grant CEP: GA AV ČR IAB1030006; GA AV ČR IAA2030801
Klíčová slova: neural networks * Kolmogorov theorem * parallelization
Kód oboru RIV: BA - Obecná matematika
A thorough analysis of theoretical and computational properties of kolmogorov learning algorithm for feedforward neural networks lead us to proposal of efficient sequential and parallel implementation. A novel approach to parallelization which combines our previous results in order to achieve higher parallel speedup is presented.
Trvalý link: http://hdl.handle.net/11104/0124868
Počet záznamů: 1