Transformers have become the dominant model in deep learning, but the re...
Recent architectural developments have enabled recurrent neural networks...
To make reinforcement learning more sample efficient, we need better cre...
Identifying unfamiliar inputs, also known as out-of-distribution (OOD)
d...
State-of-the-art meta-learning techniques do not optimize for zero-shot
...
Equilibrium systems are a powerful way to express neural computations. A...
Finding neural network weights that generalize well from small datasets ...
Continual Learning (CL) algorithms have recently received a lot of atten...
Averaging the predictions of many independently trained neural networks ...