ANN Activation Function Comparative Study for Sinusoidal Data

Abstract An artificial neural network (ANN) has neurons that are interconnected. Inside the neuron, there is an activation function determines value issued by neuron. There several types of functions. The choice will determine result ANN. This paper describes performance comparison functions used in ANN processing sinusoidal signals. three being compared, those Sigmoid, Tansig, and ReLU. dataset come from simulation data PMSM FOC control process. results indicated Tansig best for sinusoid data.