Neural Networks & Deep Learning
概念
核心技术
The substrate: layered functions tuned by gradient descent.
您正在查看一条概念解释记录：该术语的通俗含义，以及它所关联的各条目。
A neural network is a stack of simple mathematical layers whose millions to trillions of weights are adjusted by backpropagation until outputs match training targets. 'Deep learning' is the discovery — mainstream since AlexNet in 2012 — that with enough layers, data and GPU compute, this recipe learns almost anything. Everything else on this site is scaffolding around that fact.
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
来源
记录审阅截至 2026-01-15 — 查看 方法论.