.png){kind=icon}
返回
Robust Learning with Implicit Residual Networks
.png){kind=icon}
OA
AI
DOI：10.3390/make3010003.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this effort, we propose a new deep architecture utilizing residual blocks inspired by implicit discretization schemes. As opposed to the standard feed-forward networks, the outputs of the proposed implicit residual blocks are defined as the fixed points of the appropriately chosen nonlinear transformations. We show that this choice leads to the improved stability of both forward and backward propagations, has a favorable impact on the generalization power, and allows for control the robustness of the network with only a few hyperparameters. In addition, the proposed reformulation of ResNet does not introduce new parameters and can potentially lead to a reduction in the number of required layers due to improved forward stability. Finally, we derive the memory-efficient training algorithm, propose a stochastic regularization technique, and provide numerical results in support of our findings.
Keyword:
ResNet
stability
robust
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
M
IF:
6
论文数:
825
被引数:
1.8K
机构
引用论文
Differential effects of plant root systems on nickel, copper and silver bioavailability in contaminated soil.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏分享收藏
分享收藏
查看更多内容