Update description GNN and Physics

Author: bricaud

studentprojects.md

@@ -44,9 +44,9 @@ In this project we will make use of simple and advanced tools from network analy
 
 - [x] Master project
 
-**Goal:** Get inspiration from Physics to design new neural network achitectures. The Laplacian is an operator that is present in Partial Differential Equations and also in graphs. Through this connection we can build new graph neural network achitectures inspired by Physics and inheriting some properties of partial differential equations.
+**Goal:** Get inspiration from Physics to design new neural network achitectures. The Laplacian is an operator that is present in Partial Differential Equations and also in graphs. Through this connection we can build new graph neural network achitectures inspired by Physics and inheriting some properties of partial differential equations. The connection between Physics and Machine Learning is a growing and promising direction of research. Some recent studies relates differential equations and graphs [Graph neural diffusion](https://proceedings.mlr.press/v139/chamberlain21a.html) and [neural diffusion and beyond](https://arxiv.org/abs/2310.10121). Moreover, interesting results were found by Tobias Antonsen during his Master project at UiT ([Propagating information like waves in GNNs](https://munin.uit.no/handle/10037/34272)). We want to continue in this direction, exploring other physics equations, possibly related to fuild mechanics and test our models on different datasets, with noisy data.
 
-This is a project focused on the theoretical aspects, involving some maths with graph theory and machine learning and some Python programming.
+This is a project focused on the theoretical aspects, involving some maths with graph theory and machine learning and some Python programming. 
 
 **Contact:** Benjamin Ricaud
 
@@ -97,4 +97,4 @@ The project will aim at improving and extending with new functionalities a recen
 **Description:** This is a theoretical project that aims at representing a real-valued time series with a graph, using tools such as the [horizontal visibility graph](https://arxiv.org/abs/1002.4526).
 By studying the properties of such a graph it is possible to gain new insights about the properties of the dynamical system, from where the original time series comes from.
 
-**Contact:** Filippo M. Bianchi
+**Contact:** Filippo M. Bianchi