In many cases an activation function is notated as g (e.g. Andrew Ng's Course courses), especially if it doesn't refer to any specific activation function such as sigmoid.

However, where does this convention come from? And for what reason did g start to be used?

  • 1
    $\begingroup$ It’s just a notation. You can call it whatever you want. a BC d $\endgroup$ – Vivek Khetan Nov 3 '17 at 12:25
  • $\begingroup$ Yes but what is the reason? That is the point of my question. $\endgroup$ – Blaszard Nov 3 '17 at 13:12
  • $\begingroup$ Read some linear algebra. $\endgroup$ – Vivek Khetan Nov 3 '17 at 13:30
  • 2
    $\begingroup$ That is not an answer. $\endgroup$ – Blaszard Nov 6 '17 at 10:03
  • $\begingroup$ ESL uses $\sigma(.)$. This is a dumb question. $\endgroup$ – generic_user Nov 6 '17 at 21:37

The addition of the activation layer creates a composition of two functions.

"A general function, to be defined for a particular context, is usually denoted by a single letter, most often the lower-case letters f, g, h."

So it comes down to the reason that he uses the hypothesis representation h(x)=wX+b which is a function, and that is wrapped by an activation function denoted as g. The choice of g seems to be purely alphabetical.

  • $\begingroup$ He didn't write the hypothesis function as h; he used z. So it was not intuitive for me why he used g... $\endgroup$ – Blaszard Nov 9 '17 at 19:28

Your Answer

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

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