From ce11ffd2ac98b0f28f50954c328aa8e295ece017 Mon Sep 17 00:00:00 2001 From: Olivier Cots <olivier.cots@irit.fr> Date: Mon, 2 Sep 2024 15:08:00 +0200 Subject: [PATCH] up readme --- README.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 2452d98..582b733 100644 --- a/README.md +++ b/README.md @@ -42,4 +42,8 @@ Si vous vous demandez à quoi peut servir le calcul de dérivées et les équati - [Generalizing Scientific Machine Learning and Differentiable Simulation Beyond Continuous models](https://www.stochasticlifestyle.com/ddps-seminar-talk-generalizing-scientific-machine-learning-and-differentiable-simulation-beyond-continuous-models/) de Christopher Rackauckas (MIT). ->The combination of scientific models into deep learning structures, commonly referred to as scientific machine learning (SciML), has made great strides in the last few years in incorporating models such as ODEs and PDEs into deep learning through differentiable simulation. However, the vast space of scientific simulation also includes models like jump diffusions, agent-based models, and more. Is SciML constrained to the simple continuous cases or is there a way to generalize to more advanced model forms? This talk will dive into the mathematical aspects of generalizing differentiable simulation to discuss cases like chaotic simulations, differentiating stochastic simulations like particle filters and agent-based models, and solving inverse problems of Bayesian inverse problems (i.e. differentiation of Markov Chain Monte Carlo methods). We will then discuss the evolving numerical stability issues, implementation issues, and other interesting mathematical tidbits that are coming to light as these differentiable programming capabilities are being adopted. \ No newline at end of file +>The combination of scientific models into deep learning structures, commonly referred to as scientific machine learning (SciML), has made great strides in the last few years in incorporating models such as ODEs and PDEs into deep learning through differentiable simulation. However, the vast space of scientific simulation also includes models like jump diffusions, agent-based models, and more. Is SciML constrained to the simple continuous cases or is there a way to generalize to more advanced model forms? This talk will dive into the mathematical aspects of generalizing differentiable simulation to discuss cases like chaotic simulations, differentiating stochastic simulations like particle filters and agent-based models, and solving inverse problems of Bayesian inverse problems (i.e. differentiation of Markov Chain Monte Carlo methods). We will then discuss the evolving numerical stability issues, implementation issues, and other interesting mathematical tidbits that are coming to light as these differentiable programming capabilities are being adopted. + +- [Partial Differential Equations for Artificial Intelligence: numerical analysis, optimal control and optimal transport](https://pde-ai.math.cnrs.fr). + +>PDE-AI is a PEPR project funded by the ANR, which gathers ten major French institutions involved in developing the mathematical analysis of AI, the study of optimization in machine learning, as well as in developing machine learning for numerical analysis and scientific computing. The institutions are Univ. Paris-Dauphine (PSL), Univ. Paris-Cité, Sorbonne Univ., Univ. Paris-Saclay, Univ. Toulouse, Univ. Lyon (CNRS), Univ. Bordeaux, Univ. Côte d’Azur, CREST (ENSAE/Institut Polytechnique de Paris) and Univ. Strasbourg. The project started in September 2023 and will last until 31 August 2027. The project is supported by the “France 2030” programme. \ No newline at end of file -- GitLab