Patrick Kidger

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/