Learning features from data is one of the defining characteristics of de...
Recently, Miller et al. showed that a model's in-distribution (ID) accur...
The principle of Maximal Coding Rate Reduction (MCR^2) has recently been...
Many hierarchical reinforcement learning (RL) applications have empirica...
We empirically show that the test error of deep networks can be estimate...
Current deep learning architectures suffer from catastrophic forgetting,...