Diverse studies in systems neuroscience begin with extended periods of training known as'
shaping'procedures. These involve progressively studying component parts of more …

Why do biological and artificial neurons sometimes modularise, each encoding a single
meaningful variable, and sometimes entangle their representation of many variables? In this …

Compositionality is believed to be fundamental to intelligence. In humans, it underlies the
structure of thought, language, and higher-level reasoning. In AI, compositional …

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 …

In this work, we tackle a challenging and extreme form of subpopulation shift, which is
termed compositional shift. Under compositional shifts, some combinations of attributes are …

Many tasks can be composed from a few independent components. This gives rise to a
combinatorial explosion of possible tasks, only some of which might be encountered during …

Compositional generalization (the ability to respond correctly to novel combinations of
familiar components) is thought to be a cornerstone of intelligent behavior. Compositionally …

As Transformer models grow in complexity, their ability to generalize to novel, compositional
tasks becomes crucial. This study challenges conventional wisdom about sparse activation …

Artificial and biological neurons sometimes modularise into disjoint groups each encoding a
single meaningful variable; at other times they entangle the representation of many …