Felix Köhler's Projects
A collection of wallpapers
An overview of major automatic differentiation primitive rules
A collection of possible timesteppers for the Burgers equation.
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
A collection of pullback rules, using function calls from various deep learning libraries. This also explains the handling of batch and channel axes.
Convenience wrappers to incomplete factorizations from CUSPARSE to be used for iterative solvers of sparse linear systems on the GPU
Simple implementation of Deep Operator Networks (DeepONets) in the JAX deep learning framework together with Equinox.
Test for setting up public documentation for a Python package
Online visualization tool for basic engineering math concepts using flask and bokeh. Available online at http://expmath.math.nat.tu-bs.de/ (in German)
New Version of Expmath, partiall using the old Expmath but inside new streamlit environment
Simple implementation of Fourier Neural Operators (FNOs) in the JAX deep learning framework together with Equinox.
Relating functions to their discrete Fourier coefficients
A collection of advanced autodiff primitive that built upon the implicit function theorem both for discrete problems (like solving linear systems of equations) and (semi-)continuous problems (like differential equations)
Differentiable Fluid Dynamics Package
Simple D2Q9 Lattice-Boltzmann-Method solver implemented in Python with JAX. Simulates the fluid motion of the van-Karman vortex street behind a cylinder.
An overview of various training setups for learning Neural timesteppers that approximate the step-wise solution to Partial Differential Equations (PDEs)
Solving the Navier-Stokes Equations in Python 🐍 simply using NumPy.
All the handwritten notes 📝 and source code files 🖥️ used in my YouTube Videos on Machine Learning & Simulation (https://www.youtube.com/channel/UCh0P7KwJhuQ4vrzc3IRuw4Q)
Simple implementation of Physics-Informed Neural Networks for the solution of Partial Differential Equations in JAX (using Equinox and Optax)
Simple implementation of Physics-Informed Neural Networks for the solution of Partial Differential Equations in Julia
A collection of learning setups for predictors, their primal passes and all logical backward passes. Created with draw.io
Slides + Source Code + Data for an introductory course to NumPy, Matplotlib, SciPy, Scikit-Learn & TensorFlow Keras
2D Stable Fluids & 3D Stable Fluids using the Fast Fourier Transformation implemented efficiently in Julia.