A Statistical Approach to Provide Explainable Convolutional Neural Network Parameter Optimization

DOI

10.2991/ijcis.d.191219.001How to use a DOI?

Keywords

Optimization; Convolutional neural network; Hyperparameter; Design of experiment; Taguchi; Deep learning

Abstract

Algorithms based on convolutional neural networks (CNNs) have been great attention in image processing due to their ability to find patterns and recognize objects in a wide range of scientific and industrial applications. Finding the best network and optimizing its hyperparameters for a specific application are central challenges for CNNs. Most state-of-the-art CNNs are manually designed, while techniques for automatically finding the best architecture and hyperparameters are computationally intensive, and hence, there is a need to severely limit their search space. This paper proposes a fast statistical method for CNN parameter optimization, which can be applied in many CNN applications and provides more explainable results. The authors specifically applied Taguchi based experimental designs for network optimization in a basic network, a simplified Inception network and a simplified Resnet network, and conducted a comparison analysis to assess their respective performance and then to select the hyperparameters and networks that facilitate faster training and provide better accuracy. The results show that up to a 6% increase in classification accuracy can be achieved after parameter optimization.

Copyright

© 2019 The Authors. Published by Atlantis Press SARL.

Open Access

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

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Saman Akbarzadeh
AU  - Selam Ahderom
AU  - Kamal Alameh
PY  - 2019
DA  - 2019/12/23
TI  - A Statistical Approach to Provide Explainable Convolutional Neural Network Parameter Optimization
JO  - International Journal of Computational Intelligence Systems
SP  - 1635
EP  - 1648
VL  - 12
IS  - 2
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.191219.001
DO  - 10.2991/ijcis.d.191219.001
ID  - Akbarzadeh2019
ER  -