✳flâneur — a map of the web's best reading

3Blue1Brown - Backpropagation calculus

3blue1brown.com · 3,668 words · saved by 1 readers

The hard assumption here is that you’ve read the previous part, giving an intuitive walkthrough of the backpropagation algorithm. Here, we get a bit more formal and dive into the relevant calculus. It’s normal for this to be a little confusing, so be sure to pause and ponder throughout. As a quick reminder, backpropagation is an algorithm for calculating the gradient of the cost function of a network. The entries of the gradient vector are the partial derivatives of the cost function with respect to all the different weights and biases of the network, so it’s really those derivatives that backpropagation helps us find. In the last lesson we talked about the intuitive feeling you might have for how backpropagation works, so now our focus will be on connecting that intuition with the appropriate calculus. (For those uncomfortable with the relevant calculus, I do have a whole series on the topic.) The main goal here is to show how people in machine learning commonly think about the chain

Backpropagation calculus | 3Blue1Brown Neural Networks Chapter 5 B a c k p r o p a g a t i o n c a l c u l u s The math of backpropagation, the algorithm by which neural networks learn. Nov 3, 2017 Lesson by Grant Sanderson Text adaptation by Josh Pullen Source The hard assumption here is that you've read the previous part , giving an intuitive walkthrough of the backpropagation algorithm. Here, we get a bit more formal and dive into the relevant calculus. It's normal for this to be a little confusing, so be sure to pause and ponder throughout. As a quick reminder, backpropagation is an algori

Explore this link on the map →

related reading