-2

I'm reading an article about machine learning theory, there are has a step as below to calculate partial derivative:

∂(w5 * h1 + w6 * h2 + b3) / ∂h1 = w5 * f′(w5 * h1 + w6 * h2 + b3)

As I understand the caclulation method of partial derivative, the result of ∂(w5 * h1 + w6 * h2 + b3) / ∂h1 should be w5, should not be w5 * f′(w5 * h1 + w6 * h2 + b3), I'm very confused this step, could you tell me some explain? Thank you.

desertnaut
  • 57,590
  • 26
  • 140
  • 166
sunjinbo
  • 2,137
  • 4
  • 22
  • 45
  • 1) What you understand is "derivative", not "partial derivative" - you'd only get a plain `w5` if everything except `h1` was a constant. 2) Can't say more without more context (e.g. what article). 3) Maths, not programming, thus probably off-topic here. – Amadan Aug 13 '19 at 04:10

1 Answers1

1

I believe there is a typo in the formula that you are reading. 

∂f(w5 * h1 + w6 * h2 + b3) / ∂h1 = w5 * f′(w5 * h1 + w6 * h2 + b3)

I believe there should be an f on the LHS of the equation, after which, chain rule is being applied.

If f is absent, then you are right.

Siong Thye Goh
  • 3,518
  • 10
  • 23
  • 31
  • Yes, I read the article again, you are right, I didn't notice the f on the LHS of the equation, thank you very much. – sunjinbo Aug 13 '19 at 05:11