DINCAE (Data-Interpolating Convolutional Auto-Encoder) is a neural network to reconstruct missing data in satellite observations.

Implementations of Infinitesimal Continuous Normalizing Flows Algorithms in Julia

The Julia implementation of the generalised hierarchical Gaussian filter

Differentiable tree-based models for tabular data

SeaPearl's pool of examples

A package to calibrate atmospheric turbulence and convection parameterizations using gradient-free ensemble Kalman methods

General Relativistic Orbital Dynamics in Julia

Lazy, structured, and efficient operations with kernel matrices.

-

Easily optimize generic performance metrics in differentiable learning.

From Semiconductor to TransistorLevel Modeling in Julia

Simple, blazing fast, transformer components.

MeshGraphNets.jl is a software package for the Julia programming language that provides an implementation of the MeshGraphNets framework by Google DeepMind for simulating mesh-based physical systems via graph neural networks.

Integrating Neural Ordinary Differential Equations, the Method of Lines, and Graph Neural Networks

Representing machine learning models using mathematical programming

Scalable nonparametric clustering with unified marker gene selection for single-cell RNA-seq data

-

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

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

Julia package for microstructure imaging

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

Differentiable JUlia ICE model

Adversarial attacks for Neural Networks written with FluxML

A differentiable parametrization of a group of unitary matrices.

Modern Hopfield layer implementations in Julia

Train and sample Restricted Boltzmann machines in Julia

Adaptive stress testing of black-box systems within POMDPs.jl

Experimental features for Flux.jl

Implementation of Integral Probability Measures in Julia

Julia package with several functions to train and analyze Autoencoder-based neural networks

Graph-building for AtomicGraphNets

Collection of layers that can perform arithmetic operations

Sklearn Interface and Distributed Training for Flux.jl

A Julia package for behavioural modeling

JutulDarcyRules: ChainRules extension to Jutul and JutulDarcy

Lightweight module of neural differential equations in Kinetic.jl

A high-performance library for gradient based quantum optimal control

-

Differentiable 2d rasterizer in Julia

Operator layers for Flux.jl that allow for the construction of Neural Operator models by using Flux's API. Useful for discretization-independent spatio-temporal ML models.