OU Portal
Log In
Welcome
Applicants
Z6_60GI02O0O8IDC0QEJUJ26TJDI4
Error:
Javascript is disabled in this browser. This page requires Javascript. Modify your browser's settings to allow Javascript to execute. See your browser's documentation for specific instructions.
{}
Close
Publikační činnost
Probíhá načítání, čekejte prosím...
publicationId :
tempRecordId :
actionDispatchIndex :
navigationBranch :
pageMode :
tabSelected :
isRivValid :
Record type:
stať ve sborníku (D)
Home Department:
Ústav pro výzkum a aplikace fuzzy modelování (94410)
Title:
Convolutional Neural Networks with Interpretable Kernels
Citace
Molek, V. a Perfiljeva, I. Convolutional Neural Networks with Interpretable Kernels.
In:
The International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making: Integrated Uncertainty in Knowledge Modelling and Decision Making 2019-03-27 Nara, Japonsko.
Švýcarsko: Springer Verlag, 2019. s. 320-332. ISBN 978-303014814-0.
Subtitle
Publication year:
2019
Obor:
Informatika
Number of pages:
12
Page from:
320
Page to:
332
Form of publication:
Tištená verze
ISBN code:
978-303014814-0
ISSN code:
0302-9743
Proceedings title:
Integrated Uncertainty in Knowledge Modelling and Decision Making
Proceedings:
Mezinárodní
Publisher name:
Springer Verlag
Place of publishing:
Švýcarsko
Country of Publication:
Sborník vydaný v zahraničí
Název konference:
The International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making
Místo konání konference:
Nara, Japonsko
Datum zahájení konference:
Typ akce podle státní
příslušnosti účastníků:
Celosvětová akce
WoS code:
EID:
2-s2.0-85064189831
Key words in English:
F-transform; convolutional kernels;convolutional neural networks;interpretability.
Annotation in original language:
We are focused on the theoretical background of convolutional neural networks. In particular, we examine the problem whether semantic meaning can be assigned to convolutional kernels in the first layers and how this fact can simplify the learning procedure.In this respect, we prove the suitability and efficiency of the F-transform kernels. We describe various experiments that support our claim.
Annotation in english language:
References
Reference
R01:
RIV/61988987:17610/19:A2001W7P
Complementary Content
Deferred Modules
${title}
${badge}
${loading}
Deferred Modules
Probíhá načítání, čekejte prosím...