Number of the records: 1
Limitations of One-Hidden-Layer Perceptron Networks
- 1.
SYSNO ASEP 0447921 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Limitations of One-Hidden-Layer Perceptron Networks Author(s) Kůrková, Věra (UIVT-O) RID, SAI, ORCID Source Title Proceedings ITAT 2015: Information Technologies - Applications and Theory. - Aachen & Charleston : Technical University & CreateSpace Independent Publishing Platform, 2015 / Yaghob J. - ISSN 1613-0073 - ISBN 978-1-5151-2065-0 Pages s. 167-171 Number of pages 5 s. Publication form Online - E Action ITAT 2015. Conference on Theory and Practice of Information Technologies /15./ Event date 17.09.2015-21.09.2015 VEvent location Slovenský Raj Country SK - Slovakia Event type EUR Language eng - English Country DE - Germany Keywords perceptron networks ; model complexity ; representations of finite mappings by neural networks Subject RIV IN - Informatics, Computer Science R&D Projects LD13002 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) Institutional support UIVT-O - RVO:67985807 EID SCOPUS 84944321547 Annotation Limitations of one-hidden-layer perceptron networks to represent efficiently finite mappings is investigated. It is shown that almost any uniformly randomly chosen mapping on a sufficiently large finite domain cannot be tractably represented by a one-hidden-layer perceptron network. This existential probabilistic result is complemented by a concrete example of a class of functions constructed using quasi-random sequences. Analogies with central paradox of coding theory and no free lunch theorem are discussed. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2016
Number of the records: 1