Optimization of Artificial Neural Networks using Wavelet Transforms

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 netw...

Täydet tiedot

Tallennettuna:

Bibliografiset tiedot
Päätekijät:	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.
Aineistotyyppi:	Статья
Kieli:	English
Julkaistu:	2023
Aiheet:	Artificial neural networks Wavelet transforms
Linkit:	https://dspace.ncfu.ru/handle/20.500.12258/22262
Tagit:	Lisää tagi Ei tageja, Lisää ensimmäinen tagi!

id	ir-20.500.12258-22262
record_format	dspace
spelling	ir-20.500.12258-222622023-01-26T14:33:49Z Optimization of Artificial Neural Networks using Wavelet Transforms 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. Artificial neural networks Wavelet transforms 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. 2023-01-26T14:32:40Z 2023-01-26T14:32:40Z 2022 Статья 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 http://hdl.handle.net/20.500.12258/22262 en Programming and Computer Software application/pdf application/pdf
institution	СКФУ
collection	Репозиторий
language	English
topic	Artificial neural networks Wavelet transforms
spellingShingle	Artificial neural networks Wavelet transforms 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. Optimization of Artificial Neural Networks using Wavelet Transforms
description	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.
format	Статья
author	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.
author_facet	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.
author_sort	Vershkov, N. A.
title	Optimization of Artificial Neural Networks using Wavelet Transforms
title_short	Optimization of Artificial Neural Networks using Wavelet Transforms
title_full	Optimization of Artificial Neural Networks using Wavelet Transforms
title_fullStr	Optimization of Artificial Neural Networks using Wavelet Transforms
title_full_unstemmed	Optimization of Artificial Neural Networks using Wavelet Transforms
title_sort	optimization of artificial neural networks using wavelet transforms
publishDate	2023
url	https://dspace.ncfu.ru/handle/20.500.12258/22262
work_keys_str_mv	AT vershkovna optimizationofartificialneuralnetworksusingwavelettransforms AT verškovna optimizationofartificialneuralnetworksusingwavelettransforms AT babenkomg optimizationofartificialneuralnetworksusingwavelettransforms AT babenkomg optimizationofartificialneuralnetworksusingwavelettransforms AT kuchukovva optimizationofartificialneuralnetworksusingwavelettransforms AT kučukovva optimizationofartificialneuralnetworksusingwavelettransforms AT kucherovnn optimizationofartificialneuralnetworksusingwavelettransforms AT kučerovnn optimizationofartificialneuralnetworksusingwavelettransforms AT kuchukovann optimizationofartificialneuralnetworksusingwavelettransforms AT kučukovann optimizationofartificialneuralnetworksusingwavelettransforms
_version_	1760600744152530944

Optimization of Artificial Neural Networks using Wavelet Transforms

Samankaltaisia teoksia