This question is a duplicate of this question on StackOverflow, but it hasn't been answered in 2 years, which is why I'm re-posting it. If this isn't an appropriate way to go about this, please let me know as I'm new to the community.

The piecewise-linear activation function as defined in Neural Networks by Simon S. Haykin has three pieces, one of which is:

$φ(v) = v, -0.5 < v < 0.5$

Haykin presents this graph of the function:

enter image description here

in which $φ(v)$ increases linearly w.r.t. $v$ in the region $-0.5<v<0.5$.

As far as I can tell, this graph doesn't describe the function above. For example, for $v = 0$, $φ(v) = 0.5$ instead of $0$. In fact, it seems that the actual definition of $φ(v)$ in that region is $φ(v) = v + 0.5$.

This mistake seems so obvious that I must be missing something.


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.