krzysztofrusek

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

posteriors

Uncertainty quantification with PyTorch

Probabilistic-Programming-and-Bayesian-Methods-for-Hackers

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

uv

An extremely fast Python package installer and resolver, written in Rust.

PythonDataScienceHandbook

Python Data Science Handbook: full text in Jupyter Notebooks

fenbux

A Simple Statistical Distribution Library in JAX

bayeux

State of the art inference for your bayesian models.

Atom_Neural_Traffic_Compression

This repository contains de code and instructions to train the models and prepare the datasets for the experiments in the paper "Atom: Neural Traffic Compression with Spatio-Temporal Graph Neural Networks" accepted at the 2nd ACM CONEXT GNNet 2023 Workshop.

materials_discovery

jeometric

Graph neural networks in JAX.

SONew

graphcast

nevergrad

A Python toolbox for performing gradient-free optimization

optimistix

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

Autodiff-Puzzles

temporian

Temporian is an open-source Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖

digraph_transformer

mojo

The Mojo Programming Language

gsd

Reference implementation of generalised score distribution in python

synjax

ccbo

This repo contains the code associated to the paper: "Constrained Causal Bayesian Optimization" by Aglietti Virginia, Alan Malek, Ira Ktena, and Silvia Chiappa. International Conference on Machine Learning. PMLR, 2023.

chex

quax

Multiple dispatch over abstract array types in JAX.

paxml

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.

lineax

Linear solvers in JAX and Equinox. https://docs.kidger.site/lineax

do-we-need-attention

equinox

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

spherical-cnn

wax-ml

A Python library for machine-learning and feedback loops on streaming data

typst_pyimage

Typst extension, adding support for generating figures using inline Python code