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

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

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

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

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

Graph Neural Networks 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.

Causal, Higher-Order, Probabilistic Programming

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

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

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

Proximal algorithms for nonsmooth optimization in Julia

Complex neural network examples for Flux.jl

Universal modeling and simulation of fluid mechanics upon machine learning. From the Boltzmann equation, heading towards multiscale and multiphysics flows.

A flexible neural net training library inspired by fast.ai

A package for Counterfactual Explanations and Algorithmic Recourse in Julia.

Toolbox for gradient-based and derivative-free non-convex constrained optimization with continuous and/or discrete variables.

Fast inference for Gaussian processes in problems involving time. Partly built on results from https://proceedings.mlr.press/v161/tebbutt21a.html

-

Explainable AI in Julia.

3D computer vision library in Julia

MagNav: airborne Magnetic anomaly Navigation

Beta Machine Learning Toolkit

Algorithms that combine tensor network methods with automatic differentiation

Pure Julia implementations of single-pass object detection neural networks.