82 Open source projects that are alternatives of or similar to MissionImpossible

Source-to-Source Debuggable Derivatives in Pure Python

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

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

A simple library for creating complex neural networks

Intimate Affection Auditor

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

Method of Manufactured Solutions Repository

Forward Mode Automatic Differentiation for Julia

Julia port of the Python autograd package.

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

Tensorlang, a differentiable programming language based on TensorFlow

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

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

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

JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"

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

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

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

Causing: CAUsal INterpretation using Graphs

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

Automatic Differentiation Library for Computational and Mathematical Engineering

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

Tensors and differentiable operations (like TensorFlow) in Rust

Source Code Generation for Automatic Differentiation using Operator Overloading

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

Differential Algebra Computational Toolbox

C++ template library for probabilistic programming

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

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

Innovative, efficient, and computational-graph-based finite element simulator for inverse modeling

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

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

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

基于Python的numpy实现的简易深度学习框架，包括自动求导、优化器、layer等的实现。

automatic differentiation made easier for C++

Heterogeneous automatic differentiation ("backpropagation") in Haskell

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.

Infinite order automatic differentiation for Monte Carlo with unnormalized probability distribution

A Programming Language for Deep Learning

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

High-performance automatic differentiation of LLVM.

Differentiable molecular simulation of proteins with a coarse-grained potential

Shape-Safe Symbolic Differentiation with Algebraic Data Types

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

🔬 Nano size Theano LSTM module

⅀

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

Julia bindings for the Enzyme automatic differentiator

A symbolic math library written in Julia modelled off scmutils

A framework for developing multi-scale arrays for use in scientific machine learning (SciML) simulations

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.

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

Algorithms that combine tensor network methods with automatic differentiation

Reverse-mode automatic differentiation in Julia

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

QuantumFlow: A Quantum Algorithms Development Toolkit

Fortran compilers, preprocessors, static analyzers, transpilers, IDEs, build systems, etc.

Efficient computations with symmetric and non-symmetric tensors with support for automatic differentiation.

ADAM implements a collection of algorithms for calculating rigid-body dynamics in Jax, CasADi, PyTorch, and Numpy.

Reverse Mode Automatic Differentiation for Julia