Convolutional Neural Networks with Interpretable Kernels
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F19%3AA2001W7P" target="_blank" >RIV/61988987:17610/19:A2001W7P - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-030-14815-7_27" target="_blank" >http://dx.doi.org/10.1007/978-3-030-14815-7_27</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-14815-7_27" target="_blank" >10.1007/978-3-030-14815-7_27</a>
Alternative languages
Result language
angličtina
Original language name
Convolutional Neural Networks with Interpretable Kernels
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10102 - Applied mathematics
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Integrated Uncertainty in Knowledge Modelling and Decision Making
ISBN
978-303014814-0
ISSN
0302-9743
e-ISSN
—
Number of pages
12
Pages from-to
320-332
Publisher name
Springer Verlag
Place of publication
Švýcarsko
Event location
Nara, Japonsko
Event date
Mar 27, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—