Improving Neural Network Approximations in Applications: Case Study in Materials Science

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F09%3A00326658" target="_blank" >RIV/67985807:_____/09:00326658 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Improving Neural Network Approximations in Applications: Case Study in Materials Science

Original language description

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 boostingis 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 detailedcase study in materials science.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

IN - Informatics

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2009

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Neural Network World

ISSN

1210-0552

e-ISSN

—

Volume of the periodical

19

Issue of the periodical within the volume

2

Country of publishing house

CZ - CZECH REPUBLIC

Number of pages

26

Pages from-to

—

UT code for WoS article

000266086700002

EID of the result in the Scopus database

—