Neuroscience has long been an important driver of progress in artificial...
Re-initializing a neural network during training has been observed to im...
Continual learning - learning new tasks in sequence while maintaining
pe...
One aim shared by multiple settings, such as continual learning or trans...
This perspective piece came about through the Generative Adversarial
Col...
Most of the recent deep reinforcement learning advances take an RL-centr...
In this paper, we propose a multi-timescale replay (MTR) buffer for impr...
Learning to produce spatiotemporal sequences is a common task the brain ...
We propose a method for tackling catastrophic forgetting in deep
reinfor...
Modern wearable rehabilitation devices and health support systems operat...
Unlike humans, who are capable of continual learning over their lifetime...
The ability to learn tasks in a sequential fashion is crucial to the
dev...