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

Bayesian Generalized Linear models using `@formula` syntax.

Turing + Makie = Turkie

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

Visualization for Flux.Chain neural networks

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

Flux's ex AD

A foolproof way of doing ML with GUI elements.

A Julia package for robust neural networks.

Generic UNet implementation written in pure Julia, based on Flux.jl

Machine learning with Mill.jl for JSON documents

Julia library for deep reinforcement learning

Import/export ONNX models

No need to train, he's a smooth operator

I heard you like compile times

Evolve Flux networks from scratch!

Interface package for featurizing atomic structures

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

Comparing performance and results of mcmc options using Julia

Clima's Land Model

-

An interface for accelerated simulation of high-dimensional collisionless and electrostatic plasmas.

A Julia implementation of sparse Gaussian processes via path-wise doubly stochastic variational inference.

Same-same but different

Common hyperparameter scheduling for ML

A time domain electrical energy grid modeling and simulation tool with a focus on the control of power electronics converters

Generative Models with trainable conditional distributions in Julia!

A turbulence-convection single column model cloud parameterization.

Neural Network based models for Natural Language Processing

-

Learning state-space targets in dynamical systems

Pruning framework and methods for Flux

An easy to use Flux implementation of the Kolmogorov Arnold Network. This is a Julia version of TorchKAN.

Neural network training, fast and easy.

Your local Flux surgeon

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