I am trying to plan a neural network for regression predictions. The final activation layer should be a linear function, but for hidden layers, do the activation functions need to also be all linear functions, or are sigmoid or ReLU functions also be in the realm of possibility? What difference would having different activation functions in hidden layers have?
-
$\begingroup$ It should be ReLU and the internet has a lot of content around this. Should check - Paper, Paper. Deep Learning Book MLP-6.3 $\endgroup$ – 10xAI Feb 11 at 7:50