Here I present the backpropagation algorithm for a continuous target variable and no activation function in hidden layer: although simpler than the one used for the logistic cost function, it's a proficuous field for math lovers.
Comment
In the "Before" calculation, the last steps, g'(x)=g'(f(3)).10, why f(3)? We said that x=2, so, could it be the following instead?
"g'(x)=g'(f(2)).10"
Thanks for sharing. Cheers.
I feel like this lends more understandable description to some of my old analysis shop's best practices (and i'm excited to translate this for mental health purposes) - thanks for this generally mind-calming share
© 2018 Data Science Central ® Powered by
Badges | Report an Issue | Privacy Policy | Terms of Service
You need to be a member of Data Science Central to add comments!
Join Data Science Central