Number of the records: 1
Improving Neural Network Approximations in Applications: Case Study in Materials Science
- 1.
SYSNO ASEP 0326658 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Improving Neural Network Approximations in Applications: Case Study in Materials Science Title Zlepšování aproximací pomocí neuronových sítí v aproximacích: případová studie v materiálových vědách Author(s) Holeňa, Martin (UIVT-O) SAI, RID
Steinfeldt, N. (DE)Source Title Neural Network World. - : Ústav informatiky AV ČR, v. v. i. - ISSN 1210-0552
Roč. 19, č. 2 (2009), s. 165-190Number of pages 26 s. Language eng - English Country CZ - Czech Republic Keywords artificial neural networks ; approximation capability ; crossvalidation Subject RIV IN - Informatics, Computer Science CEZ AV0Z10300504 - UIVT-O (2005-2011) UT WOS 000266086700002 EID SCOPUS 67649185084 Annotation The popularity of feed-forward neural networks such as multilayer perceptrons and radial basis function networks is to a large extent due to their universal approximation capability. This paper concerns its theoretical principles, together with the influence of network architecture and of the distribution of training data on this capability. Then, the possibility to exploit this influence in order to improve the approximation capability of multilayer perceptrons by means of cross-validation and boosting is explained. Although in theory, the impact of both methods on the approximation capability of feed-forward networks is known, they are still not common in real-world applications. Therefore, the paper documents usefulness of both methods on a detailed case study in materials science. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2010
Number of the records: 1