Relationship between Complexity and Precision of Convolutional Neural Networks

DOI

10.2991/isaeece-17.2017.62How to use a DOI?

Keywords

Convolutional neural networks, image classification, complexity control, complexity-precision modeling

Abstract

Convolutional neural networks (CNNs) have been successfully applied to the computer vision areas in recent years. However, these high performing CNNs generally involve intensive computation, which is unaffordable for many real-time applications. In this paper, we study the impact of four important network parameters . Then we develop mathematical models to characterize the relationship and tradeoff between the complexity C and precision P of CNNs. Once the models C( ) and P( ) are obtained, we are able to perform complexity-precision optimization to minimize the CNN complexity while achieving the target precision level by selecting the optimal configuration of four network parameters .

Copyright

© 2017, 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  - Xiaolong Ke
AU  - Wenming Cao
AU  - Fangfang Lv
PY  - 2017/03
DA  - 2017/03
TI  - Relationship between Complexity and Precision of Convolutional Neural Networks
BT  - Proceedings of the 2017 2nd International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2017)
PB  - Atlantis Press
SP  - 325
EP  - 329
SN  - 2352-5401
UR  - https://doi.org/10.2991/isaeece-17.2017.62
DO  - 10.2991/isaeece-17.2017.62
ID  - Ke2017/03
ER  -