Preprint: DNN brain alignment is nearly complete within the first 3% of training

SaxeLab · x · 2026-08-28

A new preprint shared by SaxeLab finds that brain alignment in DNNs is almost complete within the first 3% of training, while classification performance is still low at that point. The features driving classification are largely independent of those that predict brain responses, suggesting what a model learns and how brain-like it becomes may diverge very early in training.

Original post →

More from AGI Musings

AGI Musings channel →