Homepage › Solution manuals › Yaser Abu-Mostafa › Learning from Data › Exercise 7.9

Exercise 7.9

Answers

If we initialize all weights to be 0, all the inputs $s^{(l)}$ are zeros, sensitivity $δ^{(l)} = 0$ during backpropagation. So the gradient $G^{(l)} (x_{n}) = 0$ and the in-sample error $E_{in}$ is not updated through iterations.

niuers

2021-12-08 09:54

Exercise 7.9

Answers

Comments

Add answer