Felix Köhler

machine-learning-and-simulation. All the handwritten notes 📝 and source code files 🖥️ used in my YouTube Videos on Machine Learning & Simulation (https://www.youtube.com/channel/UCh0P7KwJhuQ4vrzc3IRuw4Q)

exponax. Efficient Differentiable n-d PDE Solvers in JAX.

scientific-python-course. Slides + Source Code + Data for an introductory course to NumPy, Matplotlib, SciPy, Scikit-Learn & TensorFlow Keras

pdequinox. Neural Emulator Architectures in JAX.

Tsunamis.jl. 🌊 🌊 🌊 Parallel Shallow Water Equations Solver by Finite Volume Method and HLLE Riemann Solver in Julia.

StableFluids.jl. 2D Stable Fluids & 3D Stable Fluids using the Fast Fourier Transformation implemented efficiently in Julia.

lid-driven-cavity-python. Solving the Navier-Stokes Equations in Python 🐍 simply using NumPy.

trainax. Training methodologies for autoregressive neural operators/emulators in JAX.

taylor-green-vortex-julia. A simple pseudo-spectral solver for the Direct Numerical Simulation (DNS) of the 3D Taylor-Green Vortex in the Julia programming language

expmath. Online visualization tool for basic engineering math concepts using flask and bokeh. Available online at http://expmath.math.nat.tu-bs.de/ (in German)

Lattice-Boltzmann-Method-JAX. Simple D2Q9 Lattice-Boltzmann-Method solver implemented in Python with JAX. Simulates the fluid motion of the van-Karman vortex street behind a cylinder.

UNet-in-JAX. Simple 1d UNet in JAX & Equinox to solve the Poisson equation.

FNO-in-JAX. Simple implementation of Fourier Neural Operators (FNOs) in the JAX deep learning framework together with Equinox.

4k-turbulence-wallpapers. A collection of wallpapers

pinns-in-julia. Simple implementation of Physics-Informed Neural Networks for the solution of Partial Differential Equations in Julia

pinns-in-jax. Simple implementation of Physics-Informed Neural Networks for the solution of Partial Differential Equations in JAX (using Equinox and Optax)

DeepONet-in-JAX. Simple implementation of Deep Operator Networks (DeepONets) in the JAX deep learning framework together with Equinox.

numerical_programming_cheatsheet. TeX

autodiff-table. An overview of major automatic differentiation primitive rules

chaotax. Pre-Release, please come back end of May 2026

picardax. Pre-Release, please come back end of May 2026

conv-autodiff-table-frameworks. A collection of pullback rules, using function calls from various deep learning libraries. This also explains the handling of batch and channel axes.

my-streamlit-notebooks. A collection of streamlit notebooks I found helpful in teaching me concepts

apebench-streamlit. Python

expmath_2. New Version of Expmath, partiall using the old Expmath but inside new streamlit environment

PhiML. Intuitive scientific computing with dimension types for Jax, PyTorch, TensorFlow & NumPy

hybridization-in-jax. Material for my lecture and practical session for a workshop on Machine Learning & Automatic Differentiation in JAX