# Why is an activation function notated as “g”?

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?

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

## 1 Answer

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.

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