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.

Generative Models with trainable conditional distributions in Julia!

A Julia package for Generative Topographic Mapping

-

Geometric Deep Learning for Flux

An Open-Source End-to-End Pipeline for Spiral Magnetic Resonance Image (MRI) Reconstruction in Julia

-

Representing machine learning models using mathematical programming

Integrate deep neural network and reverse mode automatic differentiation into Gauss process, have fun !

Simple, blazing fast, message-passing graph neural network.

Graph Neural Networks in Julia

Data structures for graph neural network

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

Modern Hopfield layer implementations in Julia

A Julia package for interacting with the Hugging Face dataset repository.

-

A Julia toolbox with resampling methods to correct for class imbalance.

Independent Hypothesis Weighting for multiple testing with side-information in Julia

Invariant Causal Prediction in pure Julia

Julia implementation of AlphaFold 2's Invariant Point Attention

A Julia framework for invertible neural networks

Implementation of Integral Probability Measures in Julia

Julia implementation of the ISOKANN algorithm for the computation of invariant subspaces of Koopman operators

-

Operator pack for Jets.jl. Part of the COFII framework.

Jet transform operators that depend on FFTW.jl, and Wavelets.jl. Part of the COFII framework.

Jet operator pack for seismic modeling dependent on WaveFD.jl. Part of the COFII framework.

MLJ.jl interface for JLBoost.jl

A package for Joint Energy Models and Energy-Based Models in Julia.

Machine learning with Mill.jl for JSON documents

JutulDarcyRules: ChainRules extension to Jutul and JutulDarcy

Ecosystem of numerical methods for microbial kinetics data analysis, from preprocessing to result interpretation.

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

Lightweight module of neural differential equations in Kinetic.jl

Classification algorithms based on kernel nearest centers

Koma is a Pulseq-compatible framework to efficiently simulate Magnetic Resonance Imaging (MRI) acquisitions. The main focus of this package is to simulate general scenarios that could arise in pulse sequence development.

Effortless Bayesian Deep Learning through Laplace Approximation for Flux.jl neural networks.

A neural network accelerated solver for mixed-strategy solutions of trajectory games. Do you even lift?

An adapter package that implements Lighthouse's framework interface for Flux

MagNav: airborne Magnetic anomaly Navigation