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?


Posted 2017-11-03T11:03:34.100

Reputation: 811

1It’s just a notation. You can call it whatever you want. a BC d – Vivek Khetan – 2017-11-03T12:25:43.860

Yes but what is the reason? That is the point of my question. – Blaszard – 2017-11-03T13:12:27.800

Read some linear algebra. – Vivek Khetan – 2017-11-03T13:30:26.333

2That is not an answer. – Blaszard – 2017-11-06T10:03:58.923

ESL uses $\sigma(.)$. This is a dumb question. – generic_user – 2017-11-06T21:37:34.047

@generic_user What is ESL? – Blaszard – 2017-11-13T22:37:17.757

@Blaszard https://web.stanford.edu/~hastie/ElemStatLearn/

– generic_user – 2017-11-13T23:00:38.040

"Read some linear algebra", "ESL uses $\sigma$"... Those are dumb responses. I do agree that maybe the question could be more like: "What is the standard letter for the activation function and why?" And then talk about examples like ESL uses sigma and Andrew ng uses g, etc. Because not everyone uses g for the activation function. – Agustin Barrachina – 2020-04-13T13:03:54.157



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.


Posted 2017-11-03T11:03:34.100

Reputation: 320

He didn't write the hypothesis function as h; he used z. So it was not intuitive for me why he used g... – Blaszard – 2017-11-09T19:28:26.497