Andrey Gromov | DeepAI

DeepAI

AI Chat AI Image Generator AI Video AI Music Voice Chat Studio Ghibli

Featured Co-authors

Tianyu He
16 publications
Darshil Doshi
2 publications

research

∙ 01/06/2023

Grokking modular arithmetic

We present a simple neural network that can learn modular arithmetic tas...

0 Andrey Gromov, et al. ∙

research

∙ 06/27/2022

AutoInit: Automatic Initialization via Jacobian Tuning

Good initialization is essential for training Deep Neural Networks (DNNs...

0 Tianyu He, et al. ∙

research

∙ 11/23/2021

Critical initialization of wide and deep neural networks through partial Jacobians: general theory and applications to LayerNorm

Deep neural networks are notorious for defying theoretical treatment. Ho...

0 Darshil Doshi, et al. ∙