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

Bayesian inference with probabilistic programming.

21st century AD

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

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

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

Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods

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 geospatial data science and geostatistical modeling fully written in Julia

Molecular simulation in Julia

Computational geometry in Julia

Geometric Deep Learning for Flux

Probabilistic Programming with Gaussian processes in Julia

A component of the DiffEq ecosystem for enabling sensitivity analysis for scientific machine learning (SciML). Optimize-then-discretize, discretize-then-optimize, adjoint methods, and more for ODEs, SDEs, DDEs, DAEs, etc.

A component of the DiffEq ecosystem for enabling sensitivity analysis for scientific machine learning (SciML). Optimize-then-discretize, discretize-then-optimize, adjoint methods, and more for ODEs, SDEs, DDEs, DAEs, etc.

Surrogate modeling and optimization for scientific machine learning (SciML)

Computer vision models for Flux

GPU-acceleration routines for DifferentialEquations.jl and the broader SciML scientific machine learning ecosystem

Julia package for kernel functions for machine learning

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

Graph Neural Networks in Julia

Abstract types and methods for Gaussian Processes.

Sensible extensions for exposing torch in Julia.

Research package for automatic differentiation of programs containing discrete randomness.

A Bayesian Analysis Toolkit in Julia

A package for binary and continuous, single and multi-material, truss and continuum, 2D and 3D topology optimization on unstructured meshes using automatic differentiation in Julia.

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

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

Causal, Higher-Order, Probabilistic Programming

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

Automatic differentiation of Distributions using Tracker, Zygote, ForwardDiff and ReverseDiff

Differentiable RayTracing in Julia

A Julia framework for invertible neural networks

Wrapping deep learning models from the package Flux.jl for use in the MLJ.jl toolbox

Predictive Uncertainty Quantification through Conformal Prediction for Machine Learning models trained in MLJ.

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

Proximal algorithms for nonsmooth optimization in Julia

Complex neural network examples for Flux.jl