"Neural networks" are a sad misnomer. They're neither neural nor even networks. They're chains of differentiable, parameterized geometric functions, trained with gradient descent (with gradients obtained via the chain rule). A small set of highschool-level ideas put together -via:François Chollet
“神经网络”是一个可悲的误称。它们既没有神经,也不是网络,只是可微的参数化几何函数链,用梯度下降(通过链规则获得梯度)进行训练。是一组高中水平想法的集合体
领取专属 10元无门槛券
私享最新 技术干货