Repository of best practices for deep learning in Julia, inspired by fastai

-

Computer vision models for Flux

Modular Julia-based agent framework to implement multi-agent systems

Molecular simulation in Julia

A turbulence-convection single column model cloud parameterization.

Julia package for MPI reconstruction

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

A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.

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

Composable contracts, models, and functions that allow for modeling of both simple and complex financial instruments

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

Base package that ships symbols and functionality that is relevant to all or multiple packages in the ecosystem

Lightweight module for fusing physical and neural models

Complex neural network examples for Flux.jl

Fast forward simulations of extragalactic foregrounds

Wrapping deep learning models from the package Flux.jl for use in the MLJ.jl toolbox

(Experimental) Predicting hand assignments in piano MIDI using neural networks

Implementation of advanced Sequential Monte Carlo and particle MCMC algorithms

Types and utility functions for summarizing Markov chain Monte Carlo simulations

Common abstractions for state-space models

Implementation of domain specific language (DSL) for probabilistic graphical models

Bayesian Generalized Linear models using `@formula` syntax.

Stochastic Optimization, Learning, Uncertainty and Sampling

Octofitter is a Julia package for performing Bayesian inference against direct images of exoplanets, relative astrometry, and astrometric acceleration of the host star.

-

Gila implements free space, frequency domain, electromagnetic Green functions.

A package for plotting custom symbols from Taija packages.

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

A package for wrapping iterative MLJ models in a control strategy

Fitting astrophysical star formation histories via CMD modelling.

DeepONets, (Fourier) Neural Operators, Physics-Informed Neural Operators, and more in Julia

Julia package for PEPS algorithms

A simulation engine for models related to plants

Data driven modeling and automated discovery of dynamical systems for the SciML Scientific Machine Learning organization

Implementations of the models from the Statistical Rethinking book with Turing.jl

Optimally tuned ridge regression when features can be partitioned into groups.

A flexible toolkit for simulation based inference in Julia

Julia package for microstructure imaging

Julia package with selected functions in the R package `rethinking`. Used in the SR2... projects.