-1
$\begingroup$

To design a Neural network for binary classification, We use a single neuron How to know which output function to apply in that neuron? i.e. Linear threshold or Sigmoid?

$\endgroup$
0
$\begingroup$

'Output' function? You mean activation function! It depends on your specific case. And why do you want to change it in the first place? Stick with Sigmoid until you figure out you need something else!

PS: why are you only interested in changing the activation function of the output neurons? (vs. hidden neurons as well)

$\endgroup$
2
  • $\begingroup$ It's a binary classifier so don't need hidden layers :) , I am assuming a single neuron would be sufficient looking at the data! but would adding hidden units improve accuracy? $\endgroup$
    – Saransh
    Apr 17 '17 at 12:24
  • $\begingroup$ Just because it's a binary classifier does not mean you don't need hidden layers. If your set looks like this it might not. But for more complex cases, like the XOR you're gonna need hidden neurons. $\endgroup$ Apr 17 '17 at 12:39

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.