Deep Learning and Higher Degree F-transforms: Interpretable Kernels Before and After Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F20%3AA21023D8" target="_blank" >RIV/61988987:17610/20:A21023D8 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.atlantis-press.com/journals/ijcis/125944627/view" target="_blank" >https://www.atlantis-press.com/journals/ijcis/125944627/view</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.2991/ijcis.d.200907.001" target="_blank" >10.2991/ijcis.d.200907.001</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep Learning and Higher Degree F-transforms: Interpretable Kernels Before and After Learning

Popis výsledku v původním jazyce

One of the current trends in the deep neural network technology consists in allowing a man-machine interaction and providing an explanation of network design and learning principles. In this direction, an experience with fuzzy systems is of great support. We propose our insight that is based on the particular theory of fuzzy (F)-transforms. Besides a theoretical explanation, we develop a new architecture of a deep neural network where the F-transform convolution kernels are used in the first two layers. Based on a series of experiments, we demonstrate the suitability of the F-transform-based deep neural network in the domain of image processing with the focus on recognition. Moreover, we support our insight by revealing the similarity between the F-transform and first-layer kernels in the most used deep neural networks.

Název v anglickém jazyce

Deep Learning and Higher Degree F-transforms: Interpretable Kernels Before and After Learning

Popis výsledku anglicky

One of the current trends in the deep neural network technology consists in allowing a man-machine interaction and providing an explanation of network design and learning principles. In this direction, an experience with fuzzy systems is of great support. We propose our insight that is based on the particular theory of fuzzy (F)-transforms. Besides a theoretical explanation, we develop a new architecture of a deep neural network where the F-transform convolution kernels are used in the first two layers. Based on a series of experiments, we demonstrate the suitability of the F-transform-based deep neural network in the domain of image processing with the focus on recognition. Moreover, we support our insight by revealing the similarity between the F-transform and first-layer kernels in the most used deep neural networks.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

Projekt

<a href="/cs/project/EF17_049%2F0008414" target="_blank" >EF17_049/0008414: Centrum pro výzkum a vývoj metod umělé intelligence v automobilovém průmyslu regionu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název periodika

International Journal of Computational Intelligence Systems

ISSN

1875-6891

e-ISSN

1875-6883

Svazek periodika

13

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

SG - Singapurská republika

Počet stran výsledku

10

Strana od-do

1404-1414

Kód UT WoS článku

000608285000006

EID výsledku v databázi Scopus

2-s2.0-85091564080