DeepAI

# Channel Normalization in Convolutional Neural Network avoids Vanishing Gradients

Normalization layers are widely used in deep neural networks to stabilize training. In this paper, we consider the training of convolutional neural networks with gradient descent on a single training example. This optimization problem arises in recent approaches for solving inverse problems such as the deep image prior or the deep decoder. We show that for this setup, channel normalization, which centers and normalizes each channel individually, avoids vanishing gradients, whereas, without normalization, gradients vanish which prevents efficient optimization. This effect prevails in deep single-channel linear convolutional networks, and we show that without channel normalization, gradient descent takes at least exponentially many steps to come close to an optimum. Contrary, with channel normalization, the gradients remain bounded, thus avoiding exploding gradients.

• 5 publications
• 38 publications
06/17/2021

### Backward Gradient Normalization in Deep Neural Networks

We introduce a new technique for gradient normalization during neural ne...
06/20/2020

### Blind Descent: A Prequel to Gradient Descent

We describe an alternative to gradient descent for backpropogation throu...
12/10/2017

### Gradient Normalization & Depth Based Decay For Deep Learning

In this paper we introduce a novel method of gradient normalization and ...
08/25/2020

### Channel-Directed Gradients for Optimization of Convolutional Neural Networks

We introduce optimization methods for convolutional neural networks that...
02/25/2016

### Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks

We present weight normalization: a reparameterization of the weight vect...
05/07/2020

### Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation

Un-trained convolutional neural networks have emerged as highly successf...
06/16/2020

### Cogradient Descent for Bilinear Optimization

Conventional learning methods simplify the bilinear model by regarding t...