Compositional learning of functions in humans and machines

arXiv:2403.12201v1 Announce Type: cross
Abstract: The ability to learn and compose functions is foundational to efficient learning and reasoning in humans, enabling flexible generalizations such as creating new dishes from known cooking processes. Beyond sequential chaining of functions, existing linguistics literature indicates that humans can grasp more complex compositions with interacting functions, where output production depends on context changes induced by different function orderings. Extending the investigation into the visual domain, we developed a function learning paradigm to explore the …

abstract arxiv beyond cooking cs.ai cs.hc cs.lg enabling functions humans learn linguistics literature machines processes reasoning type