Scaling Deep Neural Networks

Scaling a neural network tends to improve its quality. How to do it as to obtain the best performance increase ? Here we are particularly interested in Transformers.
Like

Share this post

Choose a social network to share with, or copy the URL to share elsewhere

This is a representation of how your post may appear on social media. The actual post will vary between social networks

Please sign in

If you are a registered user on Laidlaw Scholars Network, please sign in