research
∙
05/27/2023
On the special role of class-selective neurons in early training
It is commonly observed that deep networks trained for classification ex...
share
research
∙
02/03/2023
Blockwise Self-Supervised Learning at Scale
Current state-of-the-art deep networks are all powered by backpropagatio...
research
∙
07/16/2022
Progress and limitations of deep networks to recognize objects in unusual poses
Deep networks should be robust to rare events if they are to be successf...
research
∙
02/10/2021
Addressing the Topological Defects of Disentanglement via Distributed Operators
A core challenge in Machine Learning is to learn to disentangle natural ...
research
∙
01/03/2019