生物神经元比想象的厉害多了
Jeff Dean转发的研究表明，单个皮层神经元可执行猫狗分类、语音识别和10位奇偶校验任务，这些此前被认为需要整个神经网络。研究使用新方法揭示了生物神经元的计算复杂度远超经典感知机的人工神经元。这项工作由Ido Aizenbud及其合作者完成。
Quite interesting thread on capabilities of real biological neurons (spoiler: they're way more capab...
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! Ido Aizenbud @IdoAizenbud 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) 🔗 View Quoted Tweet 💬 9 🔄 6 ❤️ 57 👀 5033 📊 13 ⚡