Hi everyone, In, for example, a simple linear regression model, we can simply define the equation of the derivative of the cost function with 2 parameters (w, b) and then, each time we need to calculate it, it is O(1) calculation. However, in a neural network, we need backprop to calculate the der…

Reason for using BackProp for calculating derivative

rmwkwok December 2, 2023, 12:23pm 4

You said O(N+P). Why can backprop save time? ( a reference here )

1 Like

Topic		Replies	Views
Computing derivatives: why not analyticaly? Advanced Learning Algorithms week-module-2	4	462	May 26, 2023
So, why do we need back propogation? Improving Deep Neural Networks: Hyperparameter tun coursera-platform	4	498	May 11, 2023
Computation graph: N + P vs N x P Advanced Learning Algorithms week-module-2	16	697	April 1, 2024
Why only use backprop to adjust parameters? Advanced Learning Algorithms week-module-1	10	562	January 24, 2023
Didn't understand how gradient computation using back prop is order of N+P Advanced Learning Algorithms week-module-2	4	261	February 26, 2024