Number of the records: 1
Feed-Forward Neural Networks and Minimal Search Space Learning
- 1.
SYSNO ASEP 0405661 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve SCOPUS Title Feed-Forward Neural Networks and Minimal Search Space Learning Title Dopředné neuronové sítě a učení na minimálních prohledávacích prostorech Author(s) Neruda, Roman (UIVT-O) SAI, RID, ORCID Source Title WSEAS Transactions on Computers - ISSN 1109-2750
Roč. 4, č. 12 (2005), s. 1867-1872Number of pages 6 s. Language eng - English Country US - United States Keywords search space ; feed-forward networks ; genetic algorithms Subject RIV BA - General Mathematics R&D Projects GA201/05/0557 GA ČR - Czech Science Foundation (CSF) CEZ AV0Z10300504 - UIVT-O (2005-2011) EID SCOPUS 30144444499 Annotation A functional equivalence of feed-forward networks has been proposed to reduce the search space of learning algorithms. The description of equivalence classes has been used to introduce a unique parametrization property and consequently the so-called canonical parametrizations as representatives of functional equivalence classes. A novel genetic learning algorithm for RBF networks and perceptrons with one hidden layer that operates only on these parametrizations has been proposed. Experimental results show that our procedure outperforms the standard genetic learning. An important extension of theoretical results demonstrates that our approach is also valid in the case of approximation. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2006
Number of the records: 1