Top 76 automatic-differentiation open source projects

⅀

Aircraft design optimization made fast through modern automatic differentiation. Plug-and-play analysis tools for aerodynamics, propulsion, structures, trajectory design, and much, much more.

Source-to-Source Debuggable Derivatives in Pure Python

Reverse Mode Automatic Differentiation for Julia

M.I.T General Circulation Model master code and documentation repository

Introductions to key concepts in quantum machine learning, as well as tutorials and implementations from cutting-edge QML research.

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

Local, global, and beyond optimization for scientific machine learning (SciML)

Heterogeneous automatic differentiation ("backpropagation") in Haskell

A julia package for Taylor polynomial expansions in one and several independent variables.

Aesara is a fork of the Theano library that is maintained by the PyMC developers. It was previously named Theano-PyMC.

Julia port of the Python autograd package.

Automatic differentiation in C++; infinite differentiability of conditionals, loops, recursion and all things C++

Automatic Differentiation Library for Computational and Mathematical Engineering

Julia bindings for the Enzyme automatic differentiator

Source Code Generation for Automatic Differentiation using Operator Overloading

One More Einsum for Julia! With runtime order-specification and high-level adjoints for AD

Algorithms that combine tensor network methods with automatic differentiation

QuantumFlow: A Quantum Algorithms Development Toolkit

Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.

C++ template library for probabilistic programming

Differentiable interface to FEniCS for JAX using dolfin-adjoint/pyadjoint

Self-contained Machine Learning and Natural Language Processing library in Go

Intimate Affection Auditor

Owl - OCaml Scientific and Engineering Computing @ http://ocaml.xyz

PennyLane is a cross-platform Python library for differentiable programming of quantum computers. Train a quantum computer the same way as a neural network.

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

A simple library for creating complex neural networks

automatic differentiation made easier for C++

The Control Toolbox - An Open-Source C++ Library for Robotics, Optimal and Model Predictive Control

The Stan Math Library is a C++ template library for automatic differentiation of any order using forward, reverse, and mixed modes. It includes a range of built-in functions for probabilistic modeling, linear algebra, and equation solving.

Forward Mode Automatic Differentiation for Julia

A Programming Language for Deep Learning

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

High-performance automatic differentiation of LLVM.

Gorgonia is a library that helps facilitate machine learning in Go.

Shape-Safe Symbolic Differentiation with Algebraic Data Types

『ゼロから作る Deep Learning ❸』(O'Reilly Japan, 2020)

🔬 Nano size Theano LSTM module

Tensorlang, a differentiable programming language based on TensorFlow

⟨Leibniz-Grassmann-Clifford⟩ differential geometric algebra / multivector simplicial complex

Tensors and differentiable operations (like TensorFlow) in Rust

A symbolic math library written in Julia modelled off scmutils

Pytorch implementation of "DeepFlow: History Matching in the Space of Deep Generative Models"

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.

Differential Algebra Computational Toolbox

Reverse-mode automatic differentiation in Julia

A operator overloading, tape-based, reverse-mode AD

DSL for forward and reverse mode automatic differentiation in Haskell. Port of DiffSharp.

A common interface for quadrature and numerical integration for the SciML scientific machine learning organization

Differentiable Programming Tensor Networks

Bayesian Optimization in JAX

Numerically solves equations of motion for a given Hamiltonian function

A probabilistic programming language that combines automatic differentiation, automatic marginalization, and automatic conditioning within Monte Carlo methods.

A .NET library that provides fast, accurate and automatic differentiation (computes derivative / gradient) of mathematical functions.

Automatic Differentiation for Tensor Algebras

Automatic Differentiation using Pseudo Lenses. Neat.

A numerical optimisation and deep learning framework for D.

Elastic Full Waveform Inversion for Subsurface Flow Problems Using Intrusive Automatic Differentiation

Abstract operators for large scale optimization in Julia