Activation by Switch Unit of Opposite First Powers

As a crucial component for the entire structure, activation unit introduces systemic non-linearity to a convolutional neural network (CNN) when extracting multiple features from visual patterns. This paper proposes a novel and insightful activation method termed FPLUS, which exploits mathematical power function with polar signs in form. It is enlightened by common inverse operation while endowed with an intuitive meaning of bionics. The formulation is derived theoretically and its feasibility is verified through a series of experiments. Furthermore, we extend the function presented to a more generalized type called PFPLUS with two parameters that can be fixed or learnable, so as to augment its expressive capacity.