论文标题
稳定重新连接
Stable ResNet
论文作者
论文摘要
深度重新建筑已经在许多任务上实现了最先进的表现。尽管他们解决了梯度消失的问题，但随着深度变得较大，他们可能会遭受梯度爆炸（Yang等，2017）。此外，最近的结果表明，随着深度进入无穷大，Resnet可能会失去表现力（Yang等，2017，Hayou等人，2019年）。为了解决这些问题，我们引入了一种新的Resnet体系结构，称为稳定重新系统，这些结构具有稳定梯度的特性，同时确保在无限深度限制中表现出色。
Deep ResNet architectures have achieved state of the art performance on many tasks. While they solve the problem of gradient vanishing, they might suffer from gradient exploding as the depth becomes large (Yang et al. 2017). Moreover, recent results have shown that ResNet might lose expressivity as the depth goes to infinity (Yang et al. 2017, Hayou et al. 2019). To resolve these issues, we introduce a new class of ResNet architectures, called Stable ResNet, that have the property of stabilizing the gradient while ensuring expressivity in the infinite depth limit.
