Jeff Dean· @JeffDean · X·· 2026-06-13AI 评分48
AI 导读
据 Jeff Dean 转发，Ido Aizenbud 与合作者的新研究发现，单个皮层神经元能够对猫狗进行分类、识别口语单词并解决 10 位奇偶校验——这些任务此前被认为需要整个网络才能完成。
正文 · 原文
Quite interesting thread on capabilities of real biological neurons (spoiler: they're way more capable than classical artificial neurons in a perceptron) . Nice work @IdoAizenbud and collaborators!
What can a neuron compute? Real biological neurons are complex, but how capable are they? Using a new method, we found that a single cortical neuron can classify cats vs dogs, recognize spoken words, and solve 10-bit parity, all tasks thought to require entire networks. (1/15)在 X 查看被引用的帖子
来源：Jeff Dean · x.com