Convolutional Neural Network Feature Reduction Using Wavelet Transform

Electronics and Electrical Engineering 2013
Aleksandrs Ļevinskis

Paper describes wavelet transform possible application for convolutional neural networks (CNN). As it already known, wavelet transform gives good signal representation in time and frequency domains. This can be useful for CNN input feature reduction as well as architecture simplicity by using only part of coefficients. The result of work is set of experiment which enables to configure out the most appropriate coefficient part. After feature reductions and architecture simplicity achieved configuration could classify data almost ten times faster than original.

Keywords
Convolutional Neural Networks Wavelet Transform
DOI
10.5755/j01.eee.19.3.3698
Hyperlink
http://www.eejournal.ktu.lt/index.php/elt/article/view/3698/2349

Ļevinskis, A. Convolutional Neural Network Feature Reduction Using Wavelet Transform. Electronics and Electrical Engineering, 2013, Vol.19, No.3, pp.61-64. e-ISSN 2029-5731. ISSN 1392-1215. Available from: doi:10.5755/j01.eee.19.3.3698

Publication language
English (en)