Deep Learning Normalization Techniques Explained
Learn about batch normalization, its benefits in training deep networks, and the conjecture behind its effectiveness. Explore related concepts like group normalization and the types of normalization analyzed by Ioffe and Szegedy.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Batch normalization in deep learning Usman Roshan
What is batch normalization? Subtract mean and divide by variance Alternatively set input Euclidean length to 1 Speeds up training of deep networks Improves accuracy From Ioffe and Szegedy https://arxiv.org/abs/1502.0316 7
Batch normalization From Ioffe and Szegedy https://arxiv.org/abs/1502.0316 7
Batch normalization Why does it work? Conjecture: reduces internal covariate shift (ICS) ICS is the change in distribution of layer inputs caused by updates to previous layers Recent study challenges this conjecture with empirical results
Group normalization Four types of normalization: From Ioffe and Szegedy https://arxiv.org/abs/1502.0316 7
