AerosandboxAircraft design optimization made fast through modern automatic differentiation. Plug-and-play analysis tools for aerodynamics, propulsion, structures, trajectory design, and much, much more.
TangentSource-to-Source Debuggable Derivatives in Pure Python
MitgcmM.I.T General Circulation Model master code and documentation repository
QmlIntroductions to key concepts in quantum machine learning, as well as tutorials and implementations from cutting-edge QML research.
Chainrules.jlforward and reverse mode automatic differentiation primitives for Julia Base + StdLibs
Galacticoptim.jlLocal, global, and beyond optimization for scientific machine learning (SciML)
BackpropHeterogeneous automatic differentiation ("backpropagation") in Haskell
Taylorseries.jlA julia package for Taylor polynomial expansions in one and several independent variables.
AesaraAesara is a fork of the Theano library that is maintained by the PyMC developers. It was previously named Theano-PyMC.
DcppAutomatic differentiation in C++; infinite differentiability of conditionals, loops, recursion and all things C++
Adcme.jlAutomatic Differentiation Library for Computational and Mathematical Engineering
Enzyme.jlJulia bindings for the Enzyme automatic differentiator
CppadcodegenSource Code Generation for Automatic Differentiation using Operator Overloading
Omeinsum.jlOne More Einsum for Julia! With runtime order-specification and high-level adjoints for AD
Tensornetworkad.jlAlgorithms that combine tensor network methods with automatic differentiation
Qualia2.0Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.
AutopplC++ template library for probabilistic programming
Jax Fenics AdjointDifferentiable interface to FEniCS for JAX using dolfin-adjoint/pyadjoint
SpagoSelf-contained Machine Learning and Natural Language Processing library in Go
OwlOwl - OCaml Scientific and Engineering Computing @ http://ocaml.xyz
PennylanePennyLane is a cross-platform Python library for differentiable programming of quantum computers. Train a quantum computer the same way as a neural network.
ArraymancerA 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
Autodiffautomatic differentiation made easier for C++
Control ToolboxThe Control Toolbox - An Open-Source C++ Library for Robotics, Optimal and Model Predictive Control
MathThe 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.
PinocchioA fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives
EnzymeHigh-performance automatic differentiation of LLVM.
GorgoniaGorgonia is a library that helps facilitate machine learning in Go.
KotlingradShape-Safe Symbolic Differentiation with Algebraic Data Types
TensorlangTensorlang, a differentiable programming language based on TensorFlow
Grassmann.jl⟨Leibniz-Grassmann-Clifford⟩ differential geometric algebra / multivector simplicial complex
Rust AutogradTensors and differentiable operations (like TensorFlow) in Rust
Symbolics.jlA symbolic math library written in Julia modelled off scmutils
DeepFlowPytorch implementation of "DeepFlow: History Matching in the Space of Deep Generative Models"
ChainRulesCore.jlAD-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.
daceDifferential Algebra Computational Toolbox
Yota.jlReverse-mode automatic differentiation in Julia
Nabla.jlA operator overloading, tape-based, reverse-mode AD
diffhaskDSL for forward and reverse mode automatic differentiation in Haskell. Port of DiffSharp.
Quadrature.jlA common interface for quadrature and numerical integration for the SciML scientific machine learning organization
tensorgradDifferentiable Programming Tensor Networks
bayexBayesian Optimization in JAX
HamiltonianSolverNumerically solves equations of motion for a given Hamiltonian function
BirchA probabilistic programming language that combines automatic differentiation, automatic marginalization, and automatic conditioning within Monte Carlo methods.
autodiffA .NET library that provides fast, accurate and automatic differentiation (computes derivative / gradient) of mathematical functions.
ad-lensAutomatic Differentiation using Pseudo Lenses. Neat.
doptA numerical optimisation and deep learning framework for D.
FwiFlow.jlElastic Full Waveform Inversion for Subsurface Flow Problems Using Intrusive Automatic Differentiation