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

Authors

Vojtech Molek, Irina Perfilieva^*,

Institute for Research and Applications of Fuzzy Modeling, University of Ostrava, Ostrava, 701 03, Czech Republic

^*Corresponding author. Email: irina.pefilieva@osu.cz

DOI

10.2991/ijcis.d.200907.001How to use a DOI?

Keywords

F-transform; Convolutional neural network; Deep learning; Interpretability

Abstract

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.

Copyright

© 2020 The Authors. Published by Atlantis Press B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Vojtech Molek
AU  - Irina Perfilieva
PY  - 2020
DA  - 2020/09/16
TI  - Deep Learning and Higher Degree F-Transforms: Interpretable Kernels Before and After Learning
JO  - International Journal of Computational Intelligence Systems
SP  - 1404
EP  - 1414
VL  - 13
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.200907.001
DO  - 10.2991/ijcis.d.200907.001
ID  - Molek2020
ER  -