Sander Dieleman

Excellent, thanks for the heads up!

Sweet, looking forward to this! Also slightly jealous ;)

Awesome work @soumith, thanks for doing this :) Those are some incredible numbers! I knew we had some leeway on Maxwell since almost all the code out there right now...

That is awesome news! That Python wrapper looks really sweet as well, it should make Theano integration a breeze! I'd be very interested to play around with it :)

Here's an example configuration file that uses it: https://github.com/benanne/kaggle-ndsb/blob/master/configurations/convroll_all_broaden_7x7_weightdecay_resume.py#L85

Hi, I will need some more information to be able to help you with this, what was the code that resulted in this error? It would be useful to have...

The implementation follows the formulation in "Biasing RBMs to manipulate latent selectivity and sparsity" by Goh et al, 2010. The sparsity penalty is the _cross entropy_ between the activations and...

That looks like it should work. You can probably drop the term self.sparsity_target**2 since it disappears after taking the gradient anyway. Documentation is a work in progress, I hope to...

'Regular' gaussian units have a mean which is dependent on the input. It is definitely not fixed, else you couldn't really learn much with them :) Regarding fixed variance, there...

> In fact I have to reduce to learning rate greatly, to a value of 0.00001, > for the reconstructions to look reasonable (like digits) at the starting. > May...