-
I have a regularizer (the reparametrization trick for variational autoencoder for ex.) that I can only define inside the `get_output` method. I define it and add it to the `self.regularizers` list ins…
-
Reference : http://arxiv.org/abs/1312.6114
-
@twiecki @fonnesbeck
Did you guys see this workshop?
This workshop brings together developers of black box inference technologies, probabilistic programming systems, and connectionist computing fr…
-
I just had a look at caret and made a list of learners, which have not yet been integrated into mlr (at least as far as I know).
``` r
Package Function …
-
Hi,
I recently started to use Lasagne. The interface of this library is really cool, but it seems to have critical issues in either memory or optimisation.
I tested examples in `example/mnist_con…
-
Hi,
I am trying to follow DKingma/MWelling's paper at http://arxiv.org/pdf/1312.6114v10.pdf and your torch code, I am following everything in the code except that I am getting lost at use of exp…
-
I am thinking about redesigning the model structure of Chainer. It aims at following goals:
- Provide "the standard way" to define a structured model
- Provide a safe and flexible way to save and load…
-
Hi,
I tried to build the R-modular interface but make failed
> [100%] [100%] Building CXX object src/interfaces/r_modular/CMakeFiles/r_modular.dir/sg_print_functions.cpp.o
> Building CXX object src…
-
Hi Brendan,
I was just wondering if you could give me some advice on how to use `model_utils.combine_all_parameters`. I tracked down that that's where I was doing something fundamentally wrong, and I…
ghost updated
9 years ago
-
Not sure I understand the backprop through LSTM timestep lines 110-112 in `train.lua`?
Any chance of an explanation? Thanks:)
ghost updated
9 years ago