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.
More from AGI Musings
- Toby Ord: Intelligence measures may not saturate, could reach infinity — tobyordoxford · 2026-08-28
- Toby Ord: Singularity possible even with shrinking generational gains if total is unbounded — tobyordoxford · 2026-08-28
- Generation time shrinkage drives vertical asymptotes — tobyordoxford · 2026-08-28
- Toby Ord paper mathematically dissects intelligence explosions — tobyordoxford · 2026-08-28
- Thought Experiment: New Capital Forms for Outcome-Based AI Services — curious_vii · 2026-08-28
- Remember this week: possibly the last August you spend working — rand_longevity · 2026-08-28