Table of Content

Open Access iconOpen Access

ABSTRACT

New Activation Functions in CNN and Its Applications

Tomoyuki Enomoto, Kazuhiko Kakuda, Shinichiro Miura

Nihon University, Narashino, Chiba 275-8575, Japan.
* Corresponding Author: Tomoyuki Enomoto. Email: cito18002@g.nihon-u.ac.jp.

The International Conference on Computational & Experimental Engineering and Sciences 2019, 21(2), 36-39. https://doi.org/10.32604/icces.2019.05292

Abstract

In this paper, the nonlinear activation functions based on fluid dynamics are presented. We propose two types of activation functions by applying the so-called parametric softsign to the negative region. We apply the activation function to CNN (Convolutional Neural Network) which performs image recognition and approaches from multiple benchmark datasets such as MNIST, CIFAR-10. Numerical results demonstrate the workability and the validity of the present approach through comparison with other numerical performances.

Keywords


Cite This Article

APA Style
Enomoto, T., Kakuda, K., Miura, S. (2019). New activation functions in CNN and its applications. The International Conference on Computational & Experimental Engineering and Sciences, 21(2), 36-39. https://doi.org/10.32604/icces.2019.05292
Vancouver Style
Enomoto T, Kakuda K, Miura S. New activation functions in CNN and its applications. Int Conf Comput Exp Eng Sciences . 2019;21(2):36-39 https://doi.org/10.32604/icces.2019.05292
IEEE Style
T. Enomoto, K. Kakuda, and S. Miura, “New Activation Functions in CNN and Its Applications,” Int. Conf. Comput. Exp. Eng. Sciences , vol. 21, no. 2, pp. 36-39, 2019. https://doi.org/10.32604/icces.2019.05292



cc Copyright © 2019 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1444

    View

  • 1013

    Download

  • 0

    Like

Related articles

Share Link