6-8 ANN units suffice to emulate one biological neuron in practice, researcher says
aran_nayebi · x · 2026-10-04
Responding to a common misconception, NeuroAI researcher Aran Nayebi notes the past decade of research disproves the idea that artificial neurons are vastly weaker than biological ones: in practice, c = 6-8 ANN units suffice to emulate a single biological neuron, while in principle 2 ANN units are universal approximators.
He adds this is why his team maps c artificial neurons to 1 biological neuron with a small constant c when doing model-brain regressions.
More from Research
- UT Dallas Robotics Lab Pivots From Perception to Generalizable Manipulation Learning — YuXiang_IRVL · 2026-10-04
- generativist revisits Chris Olah's info theory post and the Explainability Gap — generativist · 2026-10-04
- BOSSFIGHT benchmark: GPT-6.1 Sol scores 67 running a coffee shop, but lays off the harassment complainant — LordKittyPanther · 2026-10-04
- Kepler hits server-verified 100 on all 25 ARC-AGI-3 games with Opus 5, for $777.72 — rohanpaul_ai · 2026-10-04
- What computations does a single neuron do for cognition and consciousness? Still unsolved — JoshPurtell · 2026-10-04
- Meta's RankEvolve doubles down on agent reliability, lifting auto-research accuracy 45.8% to 62.5% — dair_ai · 2026-10-04