Backpropogation faster than forwardprop

Why does backpropogation take fewer steps than forwardpropogation?
I gave an answer in 1st comment; please correct me if I am wrong.

1 Like

The reason:
In backpropagation, we already have the value in each step that we need for the next calculation, but in the case of forwardprop, we have to go through a long calculation to get the value such value of J, a etc.

1 Like

Hello @farhana_hossain,

I searched “fewer steps” in the transcript of the video and can’t find anything. Can you walk through how you came up with the idea that backprop takes “fewer steps” than forward prop?

Cheers,
Raymond

2 Likes

N x P steps in forward prop
N + P steps in backward prop

Alright, @farhana_hossain. So, it is not that backprop is faster than forward prop.

Instead, it is that computing gradients with backprop ( N + P ) is faster than computing gradients without backprop ( N x P ). Please watch the video again for getting the idea that it is not a comparison between forward prop and backprop, but a comparison between computing gradients with and without backprop.

As for why backprop is faster, I suggest this post.

Cheers,
Raymond

1 Like