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.
Hello, I’m Chems, currently studying at EPFL doing electrical engineering. I recently worked in Professor Chizat’s lab on theory of deep neural networks, specifically on how to scale them optimally.
We and selected partners, use cookies or similar technologies as specified in the cookie policy and privacy policy.
You can consent to the use of such technologies by closing this notice.
Please sign in
If you are a registered user on Laidlaw Scholars Network, please sign in