[英]Microsoft CNTK Automatic Differentiation
According to Microsoft, CNTK includes automatic differentiation. 根据Microsoft的说法,CNTK包括自动区分。 For better understanding the source (which I've successfully built) I'd like to know which C++ classes implement AD and how it is implemented in CNTK?
为了更好地理解源代码(我已经成功构建了源代码),我想知道哪些C ++类实现AD以及如何在CNTK中实现它?
CNTK class Function
implements the AD (via Gradients method, to be precise). CNTK类
Function
实现AD(准确地说,是通过Gradients方法)。 Neural networks are represented as multiple Function
compositions like g(f(x)) . 神经网络被表示为g(f(x))之类的多功能
Function
。 Then derivative of function g is computed with respect to f like this: 然后像这样计算相对于f的函数g的导数:
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.