Relax! Flux is the ML library that doesn't make you tensor

Bayesian inference with probabilistic programming.

A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.

A Julia wrapper for TensorFlow

Universal neural differential equations with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods

Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Tutorials for doing scientific machine learning (SciML) and high-performance differential equation solving with open source software.

Repository of best practices for deep learning in Julia, inspired by fastai

Julia Implementation of Transformer models

An extensible framework for high-performance geostatistics in Julia

Probabilistic programming via source rewriting

Efficient transducers for Julia

Data driven modeling and automated discovery of dynamical systems for the SciML Scientific Machine Learning organization

"Distributions" that might not add to one.

Julia package with selected functions in the R package `rethinking`. Used in the SR2... projects.

Geometric Deep Learning for Flux

Probabilistic Programming with Gaussian processes in Julia

Computer vision models for Flux

Parallelized Base functions

Fast sequential, threaded, and distributed for-loops for Julia—fold for humans™

Molecular simulation in Julia

Julia package for kernel functions for machine learning

Types and utility functions for summarizing Markov chain Monte Carlo simulations

Utility package for accessing common Machine Learning datasets in Julia

Stan.jl illustrates the usage of the 'single method' packages, e.g. StanSample, StanOptimize, etc.

Robust, modular and efficient implementation of advanced Hamiltonian Monte Carlo algorithms

Abstract types and methods for Gaussian Processes.

A Bayesian Analysis Toolkit in Julia

Causal, Higher-Order, Probabilistic Programming

Implementations of the models from the Statistical Rethinking book with Turing.jl

Graph Neural Networks in Julia

DeepONets, (Fourier) Neural Operators, Physics-Informed Neural Operators, and more in Julia

Differentiable RayTracing in Julia

Julia hybrid constraint programming solver enhanced by a reinforcement learning driven search.

A beautifully Julian topology optimization package.

Gaussian Process package based on data augmentation, sparsity and natural gradients

Update immutable data

Extension functionality which uses Stan.jl, DynamicHMC.jl, and Turing.jl to estimate the parameters to differential equations and perform Bayesian probabilistic scientific machine learning

Implementation of domain-specific language (DSL) for dynamic probabilistic programming