Extraction of Rules from Data using Piecewise-linear Neural Networks.

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F02%3A06020062" target="_blank" >RIV/67985807:_____/02:06020062 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Extraction of Rules from Data using Piecewise-linear Neural Networks.
Original language description
The extraction of logical rules from data by means of artificial neural networks is receiving increasingly much attention. The meaning the extracted rules may convey is primarily determined by the set of their possible truth values, according to which two basic kinds of rules can be differentiated - Boolean and fuzzy. This paper presents a mathematically well founded approach based on piecewise-linear activation functions, which is suitable for the extraction of both kinds of rules.
Czech name
—
Czech description
—

Project
<a href="/en/project/IAB2030007" target="_blank" >IAB2030007: Neuroinformatics: computational theory of neural networks</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year
2002
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Fuzzy Systems and Soft Copmutational Intelligence in Management and Induastrial Engineering.
ISBN
975-97963-0-9
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
1-8
Publisher name
ITU Management Science Fakulty
Place of publication
Istanbul
Event location
Istanbul [TR]
Event date
May 29, 2002
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)