The next generation of machine intelligence requires the capability of continual learning to
acquire new knowledge without forgetting the old one while conserving limited computing …

Deep neural networks perform well on classification tasks where data streams are iid and
labeled data is abundant. Challenges emerge with non-stationary training data streams …

A hallmark of biological neural networks, which distinguishes them from their artificial
counterparts, is the high degree of sparsity in their activations. This discrepancy raises three …

Continuously processing a stream of not-iid data by neural models with the goal of
progressively learning new skills is largely known to introduce significant challenges …

Catastrophic forgetting remains a significant challenge to continual learning for decades.
While recent works have proposed effective methods to mitigate this problem, they mainly …

Catastrophic forgetting remains an outstanding challenge in continual learning. Recently,
methods inspired by the brain, such as continual representation learning and memory …

Continual learning emerges as a framework that trains the model on a sequence of tasks
without forgetting previously learned knowledge, which has been applied in multiple …

Classical models of memory in psychology and neuroscience rely on similarity-based
retrieval of stored patterns, where similarity is a function of retrieval cues and the stored …

Biologically inspired neural networks offer alternative avenues to model data distributions.
FlyVec is a recent example that draws inspiration from the fruit fly's olfactory circuit to tackle …

Clustering is a fundamental unsupervised learning problem, and recent work showed
modern continuous associative memory (AM) networks can learn to cluster data via a novel …