First Power Linear Unit with Sign
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 under conditions of some prior knowledge and anticipative properties, and then its feasibility is verified through a series of experiments using typical benchmark datasets, whose results indicate our approach owns superior competitiveness among numerous activation functions, as well as compatible stability across many CNN architectures. 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, and outcomes of identical tests validate this improvement.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Transmit power policies for stochastic stabilisation of multi-link wireless networked control systems
Transmit power control is one of the most important issues in wireless networks, where nodes typically operate on limited battery power. Reducing communicating power consumption is essential for both economic and ecologi…
Data-driven model predictive control of battery storage units
In many state-of-the-art control approaches for power systems with storage units, an explicit model of the storage dynamics is required. With growing numbers of storage units, identifying these dynamics can be cumbersome…
Model Predictive ControlCompressed Air Energy Storage-Part II: Application to Power System Unit Commitment
Unit commitment (UC) is one of the most important power system operation problems. To integrate higher penetration of wind power into power systems, more compressed air energy storage (CAES) plants are being built. Exist…
Training Neural Networks by Using Power Linear Units (PoLUs)
In this paper, we introduce "Power Linear Unit" (PoLU) which increases the nonlinearity capacity of a neural network and thus helps improving its performance. PoLU adopts several advantages of previously proposed activat…
image-classificationImage ClassificationA Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model
Learning community structures in graphs that are randomly generated by stochastic block models (SBMs) has received much attention lately. In this paper, we focus on the problem of exactly recovering the communities in a …
Stochastic Block Model