Giters

Fontinalis / fonet

fonet is a deep neural network package for Go.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Outputs only between 0 and 1

bcvery1 opened this issue · comments

commented

I'm trying to work out if this is intended behaviour, whatever data I train a network with, the output is always between 0 and 1, even if that does not match the training data.

Please see #1 as further explanation.

Have I misunderstood the scope of the networks? Is this behaviour expected? If I needed a network which was able to output a float of arbitrary size, is this possible with this package?

Many thanks

commented

Hey, it's because this package at the moment uses the sigmoid function by default which is only capable of returning values in the range of 0 <= x <= 1. You can find more about the sigmoid function here.

I was thinking about adding more functions and make it optional which should be used, also a different could be set for each layer. Maybe it's the right time to add these features!

commented

Hey @Fontinalis, thanks for the quick response. Is this something you're looking to add in the near future? I wish I could contribute, but I don't know enough about the NN methods involved!