Combining FFT and Spectral-Pooling for Efficient Convolution Neural Network Model

DOI

10.2991/aiie-16.2016.47How to use a DOI?

Keywords

computing complexity; FFT-based convolution; CS-unit

Abstract

Convolution operation is the most important and time consuming step in a convolution neural network model. In this work, we analyze the computing complexity of direct convolution and fast-Fourier-transform-based (FFT-based) convolution. We creatively propose CS-unit, which is equivalent to a combination of a convolutional layer and a pooling layer but more effective. Theoretical computing complexity of and some other similar operation is demonstrated, revealing an advantage on computation of CS-unit. Also, practical experiments are also performed and the result shows that CS-unit holds a real superiority on run time.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zelong Wang
AU  - Qiang Lan
AU  - Dafei Huang
AU  - Mei Wen
PY  - 2016/11
DA  - 2016/11
TI  - Combining FFT and Spectral-Pooling for Efficient Convolution Neural Network Model
BT  - Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)
PB  - Atlantis Press
SP  - 203
EP  - 206
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-16.2016.47
DO  - 10.2991/aiie-16.2016.47
ID  - Wang2016/11
ER  -