IMPROVING PREDICTION PERFORMANCE BY USING ASYMMETRIC TANH ACTIVATION FUNCTION

摘要

According to an aspect of the present invention, provided is an asymmetric hyperbolic tangent function (asymmetric tanh function) that can be used as an activation function regardless of the structure of a neural network. The proposed activation function limits an output range to be in between a maximum value and a minimum value of a variable to be predicted. The proposed activation function is suitable for regression problems of predicting a wide range of real values according to input data. A method comprises: calculating a weighted sum of input values at each node of an output layer of a neural network; and generating an output value by applying a nonlinear activation function to the weighted sum of the input values at each node of the output layer of the neural network.;COPYRIGHT KIPO 2020