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.

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

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

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

Probabilistic Programming with Gaussian processes in Julia

Computer vision models for Flux

Geometric Deep Learning for Flux

Julia Implementation of Transformer models

Local, global, and beyond optimization for scientific machine learning (SciML)

Surrogate modeling and optimization for scientific machine learning (SciML)

Differentiable RayTracing in Julia

Julia package for kernel functions for machine learning

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

Implementation of normalising flows and constrained random variable transformations

Turing version of StatisticalRethinking models.

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

Causal, Higher-Order, Probabilistic Programming

Abstract types and methods for Gaussian Processes.

Read ONNX graphs in Julia

An interface to the deep learning package Flux.jl from the MLJ.jl toolbox

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

Fast inference for Gaussian processes in problems involving time

3D computer vision library in Julia

Multiple Instance Learning Library is build on top of Flux.jl aimed to prototype flexible multi-instance learning models.

Implementation of the Deep Q-learning algorithm to solve MDPs

Universal modeling and simulation of fluid dynamics upon machine learning

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

I heard you like compile times

A flexible neural net training library inspired by fast.ai

Evolve Flux networks from scratch!

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

Comparing performance and results of mcmc options using Julia

A library for variational Bayesian methods in Julia

Atomic graph models for molecules and crystals in Julia

Turing + Makie = Turkie

The ideal tool for exploring global marine biogeochemical cycles.

Towards more automatic processing of structured data