Refined Max-Pooling and Unpooling Layers for Deep Convolutional Neural Networks
Konferenční objektOmezený přístuppeer-reviewedpostprintSoubory
Datum publikování
2016
Autoři
Vedoucí práce
Oponent
Název časopisu
Název svazku
Vydavatel
Vysoké učení technické v Brně
Abstrakt
The main goal of this paper is the introduction of new pooling and unpooling layers suited for deep convolutional neural networks. To this end, a new approximation of max-pooling inversion has been designed. The idea behind this approximation is also introduced in this paper. It is demonstrated on pools of size 2 x 2, with a stride of 2. The widely used technique of switches is combined with interpolation to form the new approximation. For that purpose, an unconventional expression of the switches has been used. Such an expression, allows the right placement of maxima in a reconstruction of original data, as well as interpolation of all unknown values in the reconstruction using the known maxima. The introduced inversion has been implemented into the aforementioned refined pooling and unpooling layers. Since they are suited for deep convolutional networks, behavior of the layers in the feed-forward and backpropagation passes had to be solved. In this context, the introduced conception of the switches has been further developed. Specifically, feed-forward and backpropagation switches are considered in the refined layers. One version of feed-forward and three versions of backpropagation switches have been introduced within this paper. The refined pooling and unpooling layers have been tested on a simple convolutional auto-encoder in order to verify functionality of the conception.
Rozsah stran
p. 131-142
ISSN
1803-3814
Trvalý odkaz na tento záznam
Projekt
Zdrojový dokument
Mendel 2016 : 22nd International Conference on Soft Computing
Vydavatelská verze
Přístup k e-verzi
Pouze v rámci univerzity
Název akce
Mendel 2016 : 22nd International Conference on Soft Computing (08.06.2016 - 10.06.2016)
ISBN
978-80-214-5365-4
Studijní obor
Studijní program
Signatura tištěné verze
Umístění tištěné verze
Přístup k tištěné verzi
Klíčová slova
convolutional neural network, unpooling, inversion of max-pooling, switches, deep learning, convolutional auto-encoder