Spotlight Poster

Alignment with human representations supports robust few-shot learning

Ilia Sucholutsky · Tom Griffiths

Great Hall & Hall B1+B2 (level 1) #2005
[ ]
Wed 13 Dec 8:45 a.m. PST — 10:45 a.m. PST

Abstract:

Should we care whether AI systems have representations of the world that are similar to those of humans? We provide an information-theoretic analysis that suggests that there should be a U-shaped relationship between the degree of representational alignment with humans and performance on few-shot learning tasks. We confirm this prediction empirically, finding such a relationship in an analysis of the performance of 491 computer vision models. We also show that highly-aligned models are more robust to both natural adversarial attacks and domain shifts. Our results suggest that human-alignment is often a sufficient, but not necessary, condition for models to make effective use of limited data, be robust, and generalize well.

Chat is not available.