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.

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

A flexible neural net training library inspired by fast.ai

A package for Counterfactual Explanations and Algorithmic Recourse in Julia.

SymbolicNumericIntegration.jl: Symbolic-Numerics for Solving Integrals

Fast and automatic structural identifiability software for ODE systems

-

Utilities and abstractions for Machine Learning tasks

Starter kit for legendary models

3D computer vision library in Julia

MagNav: airborne Magnetic anomaly Navigation

Optimal transport algorithms for Julia

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

Package implementing common state-space routines.

Build flexible hierarchical multi-instance learning models.

OrbitalTrajectories.jl is a modern orbital trajectory design, optimisation, and analysis library for Julia, providing methods and tools for designing spacecraft orbits and transfers via high-performance simulations of astrodynamical models.

High level functions for analyzing the output of simulations

Fast, scalable and flexible Outlier Detection with Julia

Implementation of variational Bayes inference algorithms

The amazing Reaction Mechanism Simulator for simulating large chemical kinetic mechanisms

Implementation of the Deep Q-learning algorithm to solve MDPs

Bayesian Generalized Linear models using `@formula` syntax.

A Julia package for Deep Backwards Stochastic Differential Equation (Deep BSDE) and Feynman-Kac methods to solve high-dimensional PDEs without the curse of dimensionality

Global glacier model using Universal Differential Equations for climate-glacier interactions

Turing + Makie = Turkie

Hyperparameter optimization algorithms for use in the MLJ machine learning framework

Visualization for Flux.Chain neural networks

Groebner bases in (almost) pure Julia

Model and solve optimal control problems in Julia

Atomic graph models for molecules and crystals in Julia

Use Optim to train Flux models and visualize loss landscapes

Distributed Data Parallel Training of Deep Neural Networks

FMIFlux.jl is a free-to-use software library for the Julia programming language, which offers the ability to place FMUs (fmi-standard.org) everywhere inside of your ML topologies and still keep the resulting model trainable with a standard (or custom) FluxML training process.

Efficient, Accurate, and Streamlined Training of Physics-Informed Neural Networks

A foolproof way of doing ML with GUI elements.

Flux's ex AD

GPU integrations for Dagger.jl

Implicit Layer Machine Learning via Deep Equilibrium Networks, O(1) backpropagation with accelerated convergence.

A Julia package for robust neural networks.