# How does ResNet or CNN with skip connections solve the gradient exploding problem?

I read some papers which said that the ResNet or Highway networks can mitigate the gradient vanishing/exploding problem in very deep neural networks. I'm not sure how the skip connections can solve the gradient exploding problem. Could anybody give some explanations or references? Thanks.

• Yeah, I also have not meet the exploding. But is the gradient back-propagated as you said? If y=x1+x2, then dx1=dy and dx2=dy, so if dy is large, then dx1 and dx2 are also large. If x2 is the skip connection, then the large dx2 would be back-propagated to the previous network, which I think would speed up the exploding. – mining May 8 '18 at 14:04