Parametric Flatten-T Swish: An Adaptive Nonlinear Activation Function for Deep Learning

Abstract

QActivation function is a key component in deep learning that performs non-linear mappings between the inputs and outputs. Rectified Linear Unit (ReLU) has been the most popular activation function across the deep learning community. However, ReLU contains several shortcomings that can result in inefficient training of the deep neural networks, these are: 1) the negative cancellation property of ReLU tends to treat negative inputs as unimportant information for the learning, resulting in performance degradation; 2) the inherent predefined nature of ReLU is unlikely to promote additional flexibility, expressivity, and robustness to the networks; 3) the mean activation of ReLU is highly positive and leads to bias shift effect in network layers; and 4) the multilinear structure of ReLU restricts the non-linear approximation power of the networks. To tackle these shortcomings, this paper introduced Parametric Flatten-T Swish (PFTS) as an alternative to ReLU. By taking ReLU as a baseline method, the experiments showed that PFTS improved classification accuracy on SVHN dataset by 0.31%, 0.98%, 2.16%, 17.72%, 1.35%, 0.97%, 39.99%, and 71.83% on DNN-3A, DNN-3B, DNN-4, DNN-5A, DNN-5B, DNN-5C, DNN-6, and DNN-7, respectively. Besides, PFTS also achieved the highest mean rank among the comparison methods. The proposed PFTS manifested higher non-linear approximation power during training and thereby improved the predictive performance of the networks.

Fully Kernected Neural Networks

“…Swish [29] is a nonpiecewise activation function based on Sigmoid function, which achieves better expressive power and faster convergence than ReLU. Parametric Flatten-T Swish (PFTS) [30] is an adaptive nonlinear activation function, which manifests higher nonlinear approximation power during training.…”

On Transformative Adaptive Activation Functions in Neural Networks for Gene Expression Inference

“…A parametric flatted-T swish (PFTS) [501] is an adaptive extension of the FTS (see section 3.6.46); PFTS is identical to FTS except for that the parameter T is adaptive -i.e. :…”

“…where T i is a trainable parameter for each neuron i [501]; the parameter T i is initialized to the value -0.20 [501].…”