Recent work has revealed that the neural activity patterns correlated with sensation,
cognition, and action often are not stable and instead undergo large scale changes over …

Learning continuously during all model lifetime is fundamental to deploy machine learning
solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with …

Incrementally learning new information from a non-stationary stream of data, referred to as
'continual learning', is a key feature of natural intelligence, but a challenging problem for …

Online continual learning for image classification studies the problem of learning to classify
images from an online stream of data and tasks, where tasks may include new classes …

Flexible computation is a hallmark of intelligent behavior. However, little is known about how
neural networks contextually reconfigure for different computations. In the present work, we …

Neural computations are currently investigated using two separate approaches: sorting
neurons into functional subpopulations or examining the low-dimensional dynamics of …

How are we able to learn new behaviors without disrupting previously learned ones? To
understand how the brain achieves this, we used a brain-computer interface (BCI) learning …

Biological agents are known to learn many different tasks over the course of their lives, and
to be able to revisit previous tasks and behaviors with little to no loss in performance. In …

Humans can learn several tasks in succession with minimal mutual interference but perform
more poorly when trained on multiple tasks at once. The opposite is true for standard deep …

The utility of machine learning in understanding the motor system is promising a revolution
in how to collect, measure, and analyze data. The field of movement science already …