paper-with-me

Papers

Analysis on Gradient Propagation in Batch Normalized Residual Networks

2018-12-02 · ICLR 2018 1 · Abhishek Panigrahi, Yueru Chen, C. -C. Jay Kuo

We conduct mathematical analysis on the effect of batch normalization (BN) on gradient backpropogation in residual network training, which is believed to play a critical role in addressing the gradient vanishing/explosion problem, in this work. By analyzing the mean and variance behavior of the input and the gradient in the forward and backward passes through the BN and residual branches, respectively, we show that they work together to confine the gradient variance to a certain range across residual blocks in backpropagation. As a result, the gradient vanishing/explosion problem is avoided. We also show the relative importance of batch normalization w.r.t. the residual branches in residual networks.

📄 PDF Abstract BibTeX arXiv:1812.00342

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

A Mean Field Theory of Batch Normalization

2019-02-21 · ICLR 2019 5 · Greg Yang, Jeffrey Pennington, Vinay Rao, Jascha Sohl-Dickstein 외

We develop a mean field theory for batch normalization in fully-connected feedforward neural networks. In so doing, we provide a precise characterization of signal propagation and gradient backpropagation in wide batch-n…

Normalization Gradients are Least-squares Residuals

2019-05-01 · ICLR 2019 5 · Yi Liu

Batch Normalization (BN) and its variants have seen widespread adoption in the deep learning community because they improve the training of deep neural networks. Discussions of why this normalization works so well remain…

Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion

2023-10-03 · Alexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer 외

Normalization layers are one of the key building blocks for deep neural networks. Several theoretical studies have shown that batch normalization improves the signal propagation, by avoiding the representations from beco…

ANAct: Adaptive Normalization for Activation Functions

2022-08-29 · Yuan Peiwen, Henan Liu, Zhu Changsheng, Yuyi Wang

In this paper, we investigate the negative effect of activation functions on forward and backward propagation and how to counteract this effect. First, We examine how activation functions affect the forward and backward …

Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks

2020-02-24 · NeurIPS 2020 12 · Soham De, Samuel L. Smith

Batch normalization dramatically increases the largest trainable depth of residual networks, and this benefit has been crucial to the empirical success of deep residual networks on a wide range of benchmarks. We show tha…