Implementation of Artificial Neural Networks using Arcsinh activation function
1S. S. Saranya, Ashu Prasad, Ankit Khare
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.
Artificial Neural Networks, ActivationFunctions, Training, Backpropagation