Comparison and Evaluation of Activation Functions in Term of Gradient Instability in Deep Neural Networks

Liu, Xin; Zhou, Jun; Qian, Huimin

doi:10.1109/ccdc.2019.8832578

Cited by 4 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To illustrate some of important contributions, the influence of the activation function in the convolutional neural network (CNN) model is studied in [24], improving a ReLU activation by construction of a novel surrogate. Theoretical analysis about gradient instability as well as the fundamental explanation for the exploding/vanishing gradient and the performances of different activation functions are given in [13].…”

Section: Introductionmentioning

confidence: 99%

“SPOCU”: scaled polynomial constant unit activation function

Kiseľák

Svihra

et al. 2020

Neural Comput & ApplicHas correction 2020-11-17

View full text Add to dashboard Buy / Rent full text

We address the following problem: given a set of complex images or a large database, the numerical and computational complexity and quality of approximation for neural network may drastically differ from one activation function to another. A general novel methodology, scaled polynomial constant unit activation function ''SPOCU,'' is introduced and shown to work satisfactorily on a variety of problems. Moreover, we show that SPOCU can overcome already introduced activation functions with good properties, e.g., SELU and ReLU, on generic problems. In order to explain the good properties of SPOCU, we provide several theoretical and practical motivations, including tissue growth model and memristive cellular nonlinear networks. We also provide estimation strategy for SPOCU parameters and its relation to generation of random type of Sierpinski carpet, related to the [pppq] model. One of the attractive properties of SPOCU is its genuine normalization of the output of layers. We illustrate SPOCU methodology on cancer discrimination, including mammary and prostate cancer and data from Wisconsin Diagnostic Breast Cancer dataset. Moreover, we compared SPOCU with SELU and ReLU on large dataset MNIST, which justifies usefulness of SPOCU by its very good performance.

show abstract

Section: Introductionmentioning

confidence: 99%