-
## 어떤 내용의 논문인가요? 👋
- unsupervised style transfer 의 기존 연구들에서는 content 에 독립적인 여러 attribute 들을 각각 분리해서 학습하는 접근 방식을 주로 사용합니다. (예를 들어 각 attribute 별 decoder 를 학습하거나, 각각의 attribute representation 을 학습하는 경…
-
I wrote an Edward Model like this:
```
#Constants
b_ = 24e-3
h_ = 2e-3
L_ = 120e-3
h = tf.constant(2e-3)
mbar = tf.constant(0.377)
b = ed.Normal(loc = b_, scale = b_/100)
h = ed.Normal(loc = …
-
I was wondering how a Monte Carlo estimate of ELBO should be written so that automatic differentiation correctly derives the gradient after applying score function estimator, as written in equation (3…
-
Hi all,
The `VariationalGaussianProcess` was reformulated using a `VariationalKernel` similar to the `SchurComplement`-Kernel. This kernel is defined with respect to the inducing points `Z` and con…
mrksr updated
4 years ago
-
Hi there,
I am using the [multi-output framework](https://github.com/GPflow/GPflow/blob/master/doc/source/notebooks/multioutput.ipynb), which is really great! However, I just ran into something I c…
-
The csv output is different depending on whether the CmdStan `method` is sample, optimize or variational. Right now `rstan::read_stan_csv()` is used for `method=sample`, but it doesn't work for the cs…
-
I would like to get help with creating a very simple discrete model like the Monty Hall problem without parameter learning? Not sure if this is the appropriate channel to ask this.
-
We are currently not able to compute the log probability `p(x_i | theta)` for each observation in Turing. Instead, we always compute `sum_i log p(x_i, theta)` which makes a lot of sense from an infere…
-
Hi, in bbp_homoscedastic.ipynb, it seems that you choose a normal Gaussian prior rather than a scale mixture prior. I think that mixture Gaussian prior can better model the real distribution of weight…
-
This has been a big issue for a while in that I don't support continuous output conditional probabilities or their Bayesian network counterparts.