Interpolation techniques versus F-transform in application to image reconstruction

Vlašánek, Pavel; Perfilieva, Irina

doi:10.1109/fuzz-ieee.2014.6891646

Cited by 3 publications

(1 citation statement)

References 18 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shapes of 5 × 5 kernels are generally preserved; however, some variational details were added after training.3. The shapes of 7×7 are preserved for F 1 and F 2 kernels; however the F 0 kernels became similar to the rotated F 1 6. We have employed dropout to reduce network overfitting.…”

mentioning

confidence: 99%

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

Molek¹,

Perfilieva²

2020

IJCIS

View full text Add to dashboard Cite

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.

show abstract

mentioning

confidence: 99%