To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as�…

Humans and animals have the ability to continually acquire, fine-tune, and transfer
knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is�…

The mainstream paradigm behind continual learning has been to adapt the model
parameters to non-stationary data distributions, where catastrophic forgetting is the central�…

Continual learning aims to enable a single model to learn a sequence of tasks without
catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store�…

Large transformer-based models are able to perform in-context few-shot learning, without
being explicitly trained for it. This observation raises the question: what aspects of the�…

Modern computation based on von Neumann architecture is now a mature cutting-edge
science. In the von Neumann architecture, processing and memory units are implemented�…

The fields of neuroscience and artificial intelligence (AI) have a long and intertwined history.
In more recent times, however, communication and collaboration between the two fields has�…

Artificial neural networks suffer from catastrophic forgetting. Unlike humans, when these
networks are trained on something new, they rapidly forget what was learned before. In the�…

Long-term memory formation is a major function of sleep. Based on evidence from
neurophysiological and behavioral studies mainly in humans and rodents, we consider the�…

The ability to learn tasks in a sequential fashion is crucial to the development of artificial
intelligence. Until now neural networks have not been capable of this and it has been widely�…