Learning-Activation

The choice of Activation Functions (AF) has proven to be an important factor that affects the performance of an Artificial Neural Network (ANN). Here I am using a 1-hidden layer neural network model that adapts to the most suitable activation function according to the data-set. The ANN model can learn for itself the best AF to use by exploiting a flexible functional form k0 + k1 * x with parameters k0; k1 being learned from multiple runs using backpropagation.