correct titles and add papers to Conv GP topic.

README.md

@@ -10,10 +10,11 @@ Maximillian F. Vording (PhD Student in CogSys, DTU Compute - bldg. 321, room 106
 
 ## Introducing and motivating the problem
 
-`Maybe with some plots of the data and figures illustrating the vehicles+sensors collecting it`
+`Maybe with some plots of the data and figures illustrating the vehicles+sensors collecting it
 
 ## Proposed projects outline:
 
+
 ### Variational autoencoders (VAE): 
 
 
@@ -46,34 +47,45 @@ How they are used for auto-regressive models over tagged time-series: WaveNet: [
 [The Unreasonable Effectiveness of Recurrent Neural Networks](https://karpathy.github.io/2015/05/21/rnn-effectiveness/)
 
 
-#### Deep weakly supervised learning with attention mechanisms:
-@maxvo
+
+### Deep weakly supervised learning with attention mechanisms:
 
 Attention mechanisms:
 [Attention and Augmented Recurrent Neural Networks](https://distill.pub/2016/augmented-rnns/)
 
-##### Papers:
+#### Papers:
 [[1803.02353] Multi-level Attention Model for Weakly Supervised Audio Classification](http://arxiv.org/abs/1803.02353)
 [[1903.00765] Weakly Labelled AudioSet Tagging with Attention Neural Networks  ](http://arxiv.org/abs/1903.00765)
 
-##### Git repos:
+#### Git repos:
 [qiuqiangkong/audioset_classification](https://github.com/qiuqiangkong/audioset_classification)
 
 
-#### Convolutional Gaussian processes (CGP):
-@maxvo read and define curriculum
 
-##### Blogpost Tutorials:
+### Convolutional Gaussian processes (CGP):
+
+#### Blogpost Tutorials:
 [Understanding Gaussian processes](https://peterroelants.github.io/posts/gaussian-process-tutorial/)
 
-##### Papers:
-[[1709.01894] Convolutional Gaussian Processes](https://arxiv.org/abs/1709.01894)
+#### Papers:
+
+- Introducing CGP: 
+	- [[1709.01894] Convolutional Gaussian Processes](https://arxiv.org/abs/1709.01894)
+- GPs for time-series:
+	- [Gaussian processes for time-series modelling](https://royalsocietypublishing.org/doi/10.1098/rsta.2011.0550)
+- GP regression for anomaly detection in time-series:
+	- [Anomaly detection based on data stream monitoring and prediction with improved Gaussian process regression algorithm - IEEE Conference Publication](http://ieeexplore.ieee.org/document/7036394/)
+- GP regression on binned data:
+	- [[1809.02010] Gaussian Process Regression for Binned Data ](http://arxiv.org/abs/1809.02010)
+	- [Binned Kernels for Anomaly Detection in Multi-timescale Data using Gaussian Processes](http://proceedings.mlr.press/v71/adelsberg18a.html)
 
-##### Git repos: 
+#### Git repos: 
 [markvdw/convgp: Convolutional Gaussian processes based on GPflow.
 kekeblom/DeepCGP: Deep convolutional gaussian processes.](https://github.com/markvdw/convgp)
 
-##### Tools:
-GPFlow: [Convolutional Gaussian Processes](https://gpflow.readthedocs.io/en/develop/notebooks/advanced/convolutional.html)
+#### Libraries w. GPU acceleration in Python:
+[GPFlow](https://www.gpflow.org): [Convolutional Gaussian Processes](https://gpflow.readthedocs.io/en/develop/notebooks/advanced/convolutional.html)
+
+[GPyTorch](https://gpytorch.ai)