Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I am learning about neural networks and am using the sigmoid activation function

$$q(z)=\frac{1}{1+e^{-z}}.$$ The problem is that I need to use its derivative $q^{\prime}(z)$. Would anyone have any hints as to how I would go about calculating this?

share|cite|improve this question
up vote 2 down vote accepted

Hint: $$\left(\frac 1f\right)^{\prime}=-\frac{f^{\prime}}{f^2}$$ when $f$ is non zero and differentiable. This means $$q^{\prime}(z)=\left(\frac{1}{1+e^{-z}}\right)^{\prime}=-\frac{(1+e^{-z})^{\prime}}{(1+e^{-z})^2}$$

share|cite|improve this answer
Mhh, sorry, I don't quite get more hint? :) Is it just q'(z) = q(z)^2 ? – JB2 Dec 27 '12 at 12:19
Ahh, ok, that makes sense. Thank you!! So, q'(z) = q(z)(1-q(z)). – JB2 Dec 27 '12 at 12:35

We can find the derivative of the activation function in the book "Introduction to artificial neural systems" and the author is named "WESTJACEK M. ZURADA", Professor of Electrical Engineering and of Computer Science and Engineering good luck

share|cite|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.