Probably a basic calculus question: In this video https://www.coursera.org/learn/advanced-learning-algorithms/lecture/rhcTZ/computation-graph-optional , why is there no derivative with respect to x or with respect to y? is it because the (x,y) pair is training data, we don’t take derivatives with res…

Hello @YodaKenobi , Because we only want to do gradient descent for the weights, and the gradient of the weights do not depend on any gradient of the inputs. Cheers, Raymond PS. I have added the week tag for you, and I can share a screenshot after I get to my computer in the next few hours.

C2W2: partial derivative for inputs in the `Computation Graph` video?

Course Q&A Machine Learning Specialization Advanced Learning Algorithms

rmwkwok December 27, 2023, 7:22am 3

Hello @YodaKenobi,

Please check this out for the screenshots.

Cheers,
Raymond

Topic		Replies	Views
Regression with a perceptron - gradient descent Calculus for Machine Learning and Data Science week-module-3 , dl-ai-learning-platform , coursera-platform	3	50	April 3, 2026
[Help] Derivatives Neural Networks and Deep Learning coursera-platform	3	471	June 14, 2023
C2W2 Lesson1 Gradients Quiz (Partial Derivative and Gradients) Question4 Calculus for Machine Learning and Data Science week-module-2	1	452	January 26, 2023
I have problem understanding how to compute the gradient Supervised ML: Regression and Classification week-module-2	1	541	July 21, 2022
One step of backward propagation on a computation graph yields derivative of final output variable Neural Networks and Deep Learning coursera-platform	1	441	July 20, 2023

C2W2: partial derivative for inputs in the `Computation Graph` video?

Related topics