included tempoGAN teaser

others-GANs.md

@@ -10,6 +10,15 @@ and no differentiable physics model is available to disambiguate the data. In su
 a supervised learning would yield an undesirable averaging that can be prevented with
 a GAN approach.
 
+```{figure} resources/others-GANs-tempoGAN.jpg
+---
+name: others-GANs-tempoGAN
+---
+GANs were shown to work well for tasks such 
+as the inference of super-resolution solutions where the range of possible
+results can be highly ambiguous.
+```
+
 ## Maximum Likelihood Estimation
 
 To train a GAN we have to briefly turn to classification problems.
@@ -155,6 +164,17 @@ that pushes the discriminator to take all the physical parameters under consider
 Interestingly, the generator learns to produce realistic and accurate solutions despite 
 being trained purely on data, i.e. without explicit help in the form of a differentiable physics solver setup.
 
+```{figure} resources/others-GANs-meaningful-fig11.jpg
+---
+name: others-GANs-meaningful-fig11
+---
+A range of example outputs of a physically-parametrized GAN {cite}`chu2021physgan`. 
+The network can successfully extrapolate to buoyancy settings beyond the
+range of values seen at training time.
+```
+
+
+
 ---
 
 ## Discussion

others-intro.md

@@ -16,13 +16,7 @@ More specifically, we will look at:
 * Generative models are likewise an own topic in DL, and here especially generative adversarial networks were shown to be powerful tools. They also represent a highly interesting training approach involving to separate NNs.
 
 * Meshless methods and unstructured meshes are an important topic for classical simulations. Here, we'll look at a specific Lagrangian method that employs learning in the context of dynamic, particle-based representations.
-{cite}`prantl2019tranquil`
-{cite}`ummenhofer2019contconv`
-
-https://github.com/intel-isl/DeepLagrangianFluids
 
 * Finally, metrics to robustly assess the quality of similarity of measurements and results are a central topic for all numerical methods, no matter whether they employ learning or not. In the last section we will look at how DL can be used to learn specialized and improved metrics.
+	TODO {cite}`kohl2020lsim`
 
-{cite}`kohl2020lsim`
-
-{cite}`um2020sol`