Hi,
It might be a very simple question for most of you but I am trying to
understand how exactly theano calculate its gradient.
Lets consider the example posted on Theano's documentation:
x = T.dmatrix('x')
s = T.sum(1/(1+ T.exp(-x)))
gs = T.grad(s,x)
dlogistic = function([x], gs)
dlogistic([[0, 1], [-1, -2]])
array([[ 0.25 , 0.19661193],
[ 0.19661193, 0.10499359]])
If I won't be having T.sum, then the general gradient of "s" w.r.t "x" will be
(1+ T.exp(-x)) and later I can put the value of x and will be done.
But this T.sum() operator is confusing me.
It would be great if you can help me out here.
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
