Self-gated rectified linear unit for performance improvement of deep neural networks

Self-gated rectified linear unit for performance improvement of deep neural networks

This technical paper proposes an activation function, self-gated rectified linear unit (SGReLU), to achieve high classification accuracy, low loss, and low computational time. Vanishing gradient problem, dying ReLU, noise vulnerability are also resolved in our proposed SGReLU function. SGReLU’s perf...

Full description

Bibliographic Details
Main Authors: Israt Jahan, Md. Faisal Ahmed, Md. Osman Ali, Yeong Min Jang
Format: Article
Language:English
Published: Elsevier 2023-06-01
Series:ICT Express
Subjects:
Image classification
Activation function
Deep neural network
Accuracy
Time complexity
Online Access:http://www.sciencedirect.com/science/article/pii/S2405959521001776

Internet

http://www.sciencedirect.com/science/article/pii/S2405959521001776

Similar Items