I'm new to theano, and my research group is using it as the backend for
Keras. We are using some Sparse matrices for our weights, and I wanted to
use RMSprop as our optimizer, so I had to write my own to work with these
Sparse matrices. However, I am running into errors that I don't understand.
Could you help with that?
On Thursday, September 14, 2017 at 9:11:48 PM UTC+5:30, nouiz wrote:
>
> Hi,
>
> Theano do not specify the optimizer to use. It is up to you to build your
> own optimizer.
>
> There is framework like Lasagne et Keras on top of Theano that provide
> optimizers. If you us
I have a problem while using the scan function.
What I have is, the output of the Jacobian gradient function which is a
list and I want to use it as a sequence in scan. But since scan expects a
tensor type not a list so if anyone could help me with this it would be
really helpful.
--
---
Yo
Hi,
Theano do not specify the optimizer to use. It is up to you to build your
own optimizer.
There is framework like Lasagne et Keras on top of Theano that provide
optimizers. If you use such framework, you should ask on there mailing list
how to specify your own optimizer.
Frédéric
On Wed, Sep