Implementation of Artificial Neural Networks using Arcsinh activation function

Authors

  • S. S. Saranya Assistant Professor (O.G)SRM Institute of Science and Technology Author
  • Ashu Prasad Undergraduate Student, SRM Institute of Science and Technology Author
  • Ankit Khare Undergraduate Student, SRM Institute of Science and Technology Author

DOI:

https://doi.org/10.61841/9taezc85

Keywords:

Artificial Neural Networks, Training, ActivationFunctions, Backpropagation

Abstract

This paper proposes the use of Arcsinh as an activation function to improve the efficiency of an Artificial Neural Network. The characteristics of sigmoid and Arcsinh have been articulated and Iris Dataset has been used to measure its performance. The paper attempts to strengthen its proposition of using Arcsinh activation function for multi class classification instead of sigmoid activation function by plotting the cost function of each of the activation functions with respect to the number of iterations. The plot obtained thus reveals that the Arcsinh activation function provides a better cost value when compared to the sigmoid activation function.

Downloads

Download data is not yet available.

References

1. Hudsun, Beale, M., Hagan, M.,& Demuth, H. (2015).Neural Network Toolbox.

2. Xiang Wu, Ran He, Zhenan Sun & Teiniu Tan (2018), A Light CNN for Deep Face Representation With Noisy Labels.

3. Arunselvan Ramaswamy & Shalabh Bhatnagar (2017), Analysis of Gradient Descent Methods With Non diminishing Bounded Errors.

4. Harshit Gupta, Kyong Hwan Jin, Ha Q. Ngyuen, Michael T McCann, Michael Unser (2018), CNN-BPaperedGradientDescent forConsistent CT Image Reconstruction.

5. Jun Li, Tong Zhang, Wei Luo, Jian Yang, Xiao-Tang Yuan & Jin Zhang (2017), Sparseness Analysis in the Pre training of Deep Neural Networks.

6. Gonzalo Napoles, Leonardo Concepcion, Rafael Falcon, Rafael Bello & Koen Vanhoof (2017), On the Accuracy– Convergence Tradeoff in Sigmoid Fuzzy Cognitive Maps.

7. Serwa A (2017), Studying the Effect of Activation Function on Classification Accuracy UsingDeepArtificialNeuralNetworks.

8. H.N Mhaskar & C.A Michelli(2016), How to Choose an ActivationFunction.

Downloads

Published

31.10.2020

Issue

Vol. 24 No. 8 (2020): 24 (8) 2020

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You are free to:

  1. Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
  2. Adapt — remix, transform, and build upon the material for any purpose, even commercially.
  3. The licensor cannot revoke these freedoms as long as you follow the license terms.

Under the following terms:

  1. Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  2. No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

Notices:

You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .

No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.

How to Cite

S. S. Saranya, Prasad, A., & Khare, A. (2020). Implementation of Artificial Neural Networks using Arcsinh activation function. International Journal of Psychosocial Rehabilitation, 24(8), 12980-12986. https://doi.org/10.61841/9taezc85