Immediate generalisation in humans but a generalisation lag in deep neural networks$\unicode{x2014}$evidence for representational divergence?

arXiv:2402.09303v1 Announce Type: cross
Abstract: Recent research has seen many behavioral comparisons between humans and deep neural networks (DNNs) in the domain of image classification. Often, comparison studies focus on the end-result of the learning process by measuring and comparing the similarities in the representations of object categories once they have been formed. However, the process of how these representations emerge$\unicode{x2014}$that is, the behavioral changes and intermediate stages observed during the acquisition$\unicode{x2014}$is less often directly and empirically compared.
Here we …

abstract arxiv classification comparison cs.ai cs.cv cs.lg divergence domain evidence focus humans image measuring networks neural networks process q-bio.nc research studies type unicode