Structure as an inductive bias for brain–model alignment

doi:10.1038/s42256-025-01155-y

Structure as an inductive bias for brain–model alignment

2025-12-04

0

PRE

AI

王彬旭 (Wang, Binxu)

C

Carlos R. Ponce *

DOI：10.1038/s42256-025-01155-y

Original

Original request for help

Save

Abstract

En 中文

Even before training, convolutional neural networks may reflect the brain’s visual processing principles. A study now shows how structure alone can help to explain the alignment between brains and models.

Keywords:

convolutional neural networks

brain visual processing

inductive bias

model alignment

structure-function relationship

Structure as an inductive bias for brain–model alignment

Abstract

Journal

Organization