I'm working through Deep Learning by Goodfellow et al. The textbook introduces backpropagation for MLPs in page 203 (http://www.deeplearningbook.org/contents/mlp.html). However, it does not expand further and illustrate the (full or stochastic) gradient descent update.

I'd like to confirm the full gradient descent update is as below. Is this correct?

Gradient descent derivation Gradient descent

From Deep Learning Deep Learning Backprop

  • $\begingroup$ What exactly is the part you don't understand and want to have elaborated? What exactly do you want to know about it? $\endgroup$ – Discrete lizard Feb 27 '18 at 11:44
  • 1
    $\begingroup$ Your question already includes a complete answer to the original problem but no question about this answer. Thus, only "yes/no" answers may remain, helping neither you nor future visitors. Please read related meta discussions here and here and adjust your question accordingly, e.g. by formulating a specific question about a single element of your answer you are uncertain about. If you just want general feedback, you are welcome to visit us in Computer Science Chat. $\endgroup$ – David Richerby Feb 27 '18 at 12:44
  • $\begingroup$ @Discretelizard I'd like to know whether the full gradient descent algorithm I've derived is correct or not $\endgroup$ – Black Feb 27 '18 at 12:56
  • $\begingroup$ Note that you can use LaTeX (directly, instead of in an image) here to typeset mathematics in a more readable way. See here for a short introduction. $\endgroup$ – Discrete lizard Feb 27 '18 at 13:44

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.