Relax! Flux is the ML library that doesn't make you tensor

21st century AD

Forward Mode Automatic Differentiation for Julia

Statically sized arrays for Julia

Julia implementation of Data structures

Basic statistics for Julia

Forward and reverse mode automatic differentiation primitives for Julia Base + StdLibs

Julia functional programming infrastructures and metaprogramming facilities

Heterogeneous programming in Julia

Special mathematical functions in Julia

Efficient implementation of struct arrays in Julia

Reusable array functionality for Julia's various GPU backends.

MacroTools provides a library of tools for working with Julia code and expressions.

An interface for tables in Julia

AD-backend agnostic system defining custom forward and reverse mode rules. This is the light weight core to allow you to define rules for your functions in your packages, without depending on any particular AD system.

Reduce time-to-first-execution of Julia code

Neural Network primitives with multiple backends

Lazy code loading for Julia

Julia package for lazily representing matrices filled with a single entry

Update immutable data

Update deeply nested immutable structs.

Julia macro for re-exporting one module from another

Simple Traits for Julia

Compatibility across Julia versions

Designs for new Base array interface primitives, used widely through scientific machine learning (SciML) and other organizations

Julia wrapper for the LLVM C API

Project Preferences Package

A Julia framework for implementing FFTs

Parameterise all the things

Extensions for Julia's docsystem.

Mike's Little Intermediate Representation

Utilities and abstractions for Machine Learning tasks

Uniform Interface for positive definite matrices of various structures

Package for checking function arguments

Julia implementation of associative containers that preserve insertion order

-

SparseArrays.jl is a Julia stdlib

A simple shared suite of common derivative definitions

Julia package for various special functions based on `log` and `exp`.

Optimisers.jl defines many standard optimisers and utilities for learning loops.