Author Identifier

Saman Akbarzadeh
ORCID: 0000-0003-4293-1797

Document Type

Journal Article

Publication Title

International Journal of Computational Intelligence Systems


Atlantis Press


Electron Science Research Institute




Edith Cowan University.

Grains Research and Development Corporation (GRDC).

Australian Research Council.

Photonic Detection Systems Pty. Ltd, Australia.

Pawsey Supercomputing Centre.


Akbarzadeh, S., Ahderom, S., & Alameh, K. (2019). A statistical approach to provide explainable convolutional neural network parameter optimization. International Journal of Computational Intelligence Systems, 12(2), 1635-1648.


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.



Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Included in

Engineering Commons