A new activation for neural networks and its approximation

Deep learning with deep neural networks (DNNs) has attracted tremendous attention from various fields of science and technology recently. Activation functions for a DNN define the output of a neuron given an input or set of inputs. They are essential and inevitable in learning non-linear transformations and performing diverse computations among successive neuron layers. Thus, the design of activation functions is still an important topic in deep learning research. Meanwhile, theoretical studies on the approximation ability of DNNs with activation functions have been investigated within the last few years. In this paper, we propose a new activation function, named as "DLU", and investigate its approximation ability for functions with various smoothness and structures. Our theoretical results show that DLU networks can process competitive approximation performance with rational and ReLU networks, and have some advantages. Numerical experiments are conducted comparing DLU with the existing activations-ReLU, Leaky ReLU, and ELU, which illustrate the good practical performance of DLU.