← Search

Ali Hummos

2 accepted papers

2024

Flexible task abstractions emerge in linear networks with fast and bounded units

NeurIPS 2024spotlight

Animals survive in dynamic environments changing at arbitrary timescales, but such data distribution shifts are a challenge to neural networks. To adapt to change, neural systems may change a large number of parameters, which is a slow process involving forgetting past information. In contrast, anim…

2023

Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations

ICLR 2023poster

Animals thrive in a constantly changing environment and leverage the temporal structure to learn well-factorized causal representations. In contrast, traditional neural networks suffer from forgetting in changing environments and many methods have been proposed to limit forgetting with different tra…