Gradient Descent:
反向传播求导过程:
根据链式法则(chain rule):
dj/dv = 3
dj/da = dj/dv * dv/da = 3 * 1 = 3
dj/db = dj/dv * dv/du * du/db = 3*c= 6
当你编程实现反向传播时,在代码里:dj/db写成d b 即可!
。
Gradient Descent:
反向传播求导过程:
根据链式法则(chain rule):
dj/dv = 3
dj/da = dj/dv * dv/da = 3 * 1 = 3
dj/db = dj/dv * dv/du * du/db = 3*c= 6
当你编程实现反向传播时,在代码里:dj/db写成d b 即可!
。