ChanServ changed the topic of #mlpack to: "mlpack: a fast, flexible machine learning library :: We don't always respond instantly, but we will respond; please be patient :: Logs at http://www.mlpack.org/irc/
< kartikdutt18[m]>
Ahh, no problem at all.
ImQ009 has joined #mlpack
Abilityguy has joined #mlpack
Abilityguy has quit [Remote host closed the connection]
< AakashkaushikGit>
Hi, as i can see that the activation_functions_test.cpp contains a template function for checking the forward, backward and inverse but still there is a new forward/backward function for almost every activation function even for the ones that do the same thing inside the function, is there a specific reason for that ?
< kartikdutt18Gitt>
Hey @Aakash-kaushik, the template function works for activations functions implemented in activations_functions directory. The template function function call Fn and Deriv for forward and Backward. Other than this, some activation function may require an argument that needs to be passed. So in case the activation function has some parameters or is implemented as layers we can't call the template functions.
< AakashkaushikGit>
@kartikdutt18 Got it, Thanks, I should have noticed that.