0
$\begingroup$

I am new to deep learning, and was studying about it. I know that input from input layer is multiplied with weights and then added with bias. And output of this is passed to a activation function of a neuron in hidden layer. Suppose if we use 'Relu' as activation function and our weighted sum is less than 0, then that particular neuron will not be activated right!

So similar to that what if some neuron in output layer have some value and that value is not accepted by a particular activation function means the value is below the threshold for that activation function, so will that particular neuron remain in-active.

$\endgroup$
0
$\begingroup$

Yes, it is pretty much possible that you can have an in-active neuron in an output layer.

FYI: Nodes at the input layer called passive nodes

Nodes at hidden layer called active nodes or unobservable outputs

Nodes at output layer called observable outputs

$\endgroup$

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.