The adult brain's metabolic constraints explain why brain-like learning rules fail ImageNet

ShahabBakht · x · 2026-09-15

Arguing for learning rules that match biological neural representations, the author notes the adult brain is metabolically conservative, heavily constrained, and increasingly resistant to plastic change with age. A rule operating under these constraints may look sub-optimal and fail to solve ImageNet from scratch — which is fine: the similarities are algorithmic/computational findings, not mechanistic ones.

Related event: NeuroAI Critique: Brains Don't Learn via ImageNet-Style Classification(2 posts)→

Original post →

More from Research

Research channel →