Please use this identifier to cite or link to this item:
|Title:||Optimization of Artificial Neural Networks using Wavelet Transforms|
|Authors:||Vershkov, N. A.|
Вершков, Н. А.
Babenko, M. G.
Бабенко, М. Г.
Kuchukov, V. A.
Кучуков, В. А.
Kucherov, N. N.
Кучеров, Н. Н.
Kuchukova, N. N.
Кучукова, Н. Н.
|Keywords:||Artificial neural networks;Wavelet transforms|
|Citation:||Vershkov, N., Babenko, M., Tchernykh, A., Kuchukov, V., Kucherov, N., Kuchukova, N., Drozdov, A.Yu. Optimization of Artificial Neural Networks using Wavelet Transforms // Programming and Computer Software. - 2022. - 48 (6), pp. 376-384. - DOI: 10.1134/S036176882206007X|
|Series/Report no.:||Programming and Computer Software|
|Abstract:||The article presents the artificial neural networks performance optimization using wavelet trans- form. The existing approaches of wavelet transform implementation in neural networks imply either transfor- mation before neural network or using “wavenet” architecture, which requires new neural network training approaches. The proposed approach is based on the representation of the neuron as a nonrecursive adaptive filter and wavelet filter application to obtain the low-frequency part of the image. It reduces the image size and filtering interference, which is usually high-frequency. Our wavelet transform model is based on the clas- sical representation of a forward propagation neural network or convolutional layers. It allows designing neu- ral networks with the wavelet transform based on existing libraries and does not require changes in the neural network training algorithm. It was tested on three MNIST-like datasets. As a result of testing, it was found that the speed gain is approximately 50 ± 5% with a slight loss of recognition quality of no more than 4%. For practitioner programmers, the proposed algorithm was tested on real images to distinguish animals and showed similar results as the MNIST-like tests.|
|Appears in Collections:||Статьи, проиндексированные в SCOPUS, WOS|
Files in This Item:
|scopusresults 2423 .pdf|
|542.46 kB||Adobe PDF||View/Open|
|WoS 1503 .pdf|
|113.02 kB||Adobe PDF||View/Open|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.