Name: Nathanael Bosch
Type: User
Company: University of Tübingen
Bio: PhD student at Uni Tübingen, working on machine learning and probabilistic numerics.
Twitter: nathanaelbosch
Location: Tübingen, Germany
Blog: nathanaelbosch.github.io
Nathanael Bosch's Projects
Advent of Code
Health Informatics
Fast and Accurate ML in 3 Lines of Code
Code for "Calibrated Adaptive Probabilistic ODE Solvers"
A collection of chaotic ODEs.
Benchmarking, testing, and development tools for differential equations and scientific machine learning (SciML)
Source code for DLGPD (Bosch, N., Achterhold, J., Leal-Taixé, L., Stueckler, J.): "Planning from Images with Deep Latent Gaussian Process Dynamics", in L4DC 2020
There's no place like $HOME
Master's Thesis Mathematics - Evolutionary Game Theory
Fenrir: Physics-Enhanced Regression for Initial Value Problems - Experiments
Physics-Enhanced Regression for Initial Value Problems
A package for computing matrix exponentials and finite horizon Gramians
Conway's Game of Life
Gaussian distributions as state variables and for uncertainty quantification with Unitful
PyTorch Implementation: "Optimizing the Latent Space of Generative Networks"
Only one can be Germany's Next Top Risk Model
A machine learning how to play GO - DataInnovation-Lab - WS20172018
Handy code for Gaussian filtering and smoothing enthousiasts.
A general-purpose toolbox for efficient Kronecker-based algebra.
Low Rank Approximation
Marginal distributions and Markov kernels that play nice with each other for the purpose of Bayesian state estimation.
A minimal demo for how to build ODE solvers on top of OrdinaryDiffEq.jl.
Notes for the Numerics of Machine Learning Lecture Course at the University of Tübingen
High performance differential equation solvers for ordinary differential equations, including neural ordinary differential equations (neural ODEs) and scientific machine learning (SciML)
Parallel-in-Time ODE Filters in Jax