casperkaae / parmesan

Variational and semi-supervised neural network toppings for Lasagne
Other
208 stars 31 forks source link

Some additional helper functions #35

Closed wuaalb closed 8 years ago

wuaalb commented 8 years ago

Extracted log-sum-exp from examples and added a log normal pdf parameterized with variance. Also changed sd to std and eps to epsilon for consistency with lasagne and numpy.

casperkaae commented 8 years ago

Hi

Looks good with the log-sum-exp and the sd->std. I'm not sure we should change the interface again for the eps->epsilon again though?

Casper

wuaalb commented 8 years ago

Was just for coherence with lasagne.layers.BatchNormLayer or lasagne.updates.adagrad for instance, but yeah, maybe it's too late now.. Lemme know if I should revert that change..

casperkaae commented 8 years ago

Hi again

yes I think we should revert the epsilon change (If you do not strongly object), otherwise I think it looks great!

wuaalb commented 8 years ago

I've changed back to eps.

I changed the docstrings to clarify what eps does exactly for each function, as it depends slightly on the parameterization used. There were also some T.log()s that didn't use eps.

Also added normal1 versions of the closed-form KL-divergences.