KMS Chongqing Institute of Green and Intelligent Technology, CAS
Activated Gradients for Deep Neural Networks | |
Liu, Mei1,2; Chen, Liangming1,2; Du, Xiaohao3; Jin, Long1; Shang, Mingsheng1,2,3 | |
2021-08-31 | |
摘要 | Deep neural networks often suffer from poor performance or even training failure due to the ill-conditioned problem, the vanishing/exploding gradient problem, and the saddle point problem. In this article, a novel method by acting the gradient activation function (GAF) on the gradient is proposed to handle these challenges. Intuitively, the GAF enlarges the tiny gradients and restricts the large gradient. Theoretically, this article gives conditions that the GAF needs to meet and, on this basis, proves that the GAF alleviates the problems mentioned above. In addition, this article proves that the convergence rate of SGD with the GAF is faster than that without the GAF under some assumptions. Furthermore, experiments on CIFAR, ImageNet, and PASCAL visual object classes confirm the GAF's effectiveness. The experimental results also demonstrate that the proposed method is able to be adopted in various deep neural networks to improve their performance. The source code is publicly available at https://github.com/LongJin-lab/Activated-Gradients-for-Deep-Neural-Networks. |
关键词 | Training Deep learning Neural networks Optimization Visualization Newton method Eigenvalues and eigenfunctions Exploding gradient problems gradient activation function (GAF) ill-conditioned problems saddle point problems vanishing gradient problems |
DOI | 10.1109/TNNLS.2021.3106044 |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
ISSN | 2162-237X |
页码 | 13 |
通讯作者 | Jin, Long(longjin@ieee.org) |
收录类别 | SCI |
WOS记录号 | WOS:000732099500001 |
语种 | 英语 |