research
∙
05/25/2023
SING: A Plug-and-Play DNN Learning Technique
We propose SING (StabIlized and Normalized Gradient), a plug-and-play te...
share
research
∙
11/18/2022
Improving Pixel-Level Contrastive Learning by Leveraging Exogenous Depth Information
Self-supervised representation learning based on Contrastive Learning (C...
research
∙
11/07/2022
Can neural networks extrapolate? Discussion of a theorem by Pedro Domingos
Neural networks trained on large datasets by minimizing a loss have beco...
research
∙
04/23/2022