#Automatic-differentiation
Showing 47 of 47 repositories tagged #automatic-differentiation, ranked by stars
Tensor library for machine learning
Efficiently computes derivatives of NumPy code.
Gorgonia is a library that helps facilitate machine learning in Go.
A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
Source-to-Source Debuggable Derivatives in Pure Python
Self-contained Machine Learning and Natural Language Processing library in Go
High-performance automatic differentiation of LLVM and MLIR.
21st century AD
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
Owl - OCaml Scientific Computing @ https://ocaml.xyz
『ゼロから作る Deep Learning ❸』(O'Reilly Japan, 2020)
A simple library for creating complex neural networks
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
Differentiable Fluid Dynamics Package
Julia bindings for the Enzyme automatic differentiator
🧩 Shape-Safe Symbolic Differentiation with Algebraic Data Types
Tensors and differentiable operations (like TensorFlow) in Rust
Tensor network based quantum software framework for the NISQ era
Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization
An interface to various automatic differentiation backends in Julia.
:microscope: Nano size Theano LSTM module
A deep learning framework created from scratch with Python and NumPy
A JIT compiler for hybrid quantum programs in PennyLane
Companion code for "Modern Computational Finance: AAD and Parallel Simulations" (Antoine Savine, Wiley, 2018)
PyTorch for Quantitative Finance : Refine Derivatives Hedging and Pricing with Architecture Alightment in Operators
Heterogeneous automatic differentiation ("backpropagation") in Haskell
Julia port of the Python autograd package.
Differentiable Programming Algorithms in Modern C++
Implement, demonstrate, reproduce and extend the results of the Risk articles 'Differential Machine Learning' (2020) and 'PCA with a Difference' (2021) by Huge and Savine, and cover implementation details left out from the papers.
An experimental deep learning framework for Nim based on a differentiable array programming language
Born is a modern ML framework for Go — train and deploy models as single binaries. Pure Go, zero CGO, GPU accelerated.
Generalized (hyper-) dual numbers in rust
Innovative, efficient, and computational-graph-based finite element simulator for inverse modeling
Сustom torch style machine learning framework with automatic differentiation implemented on numpy, allows build GANs, VAEs, etc.
Next-gen AI-native tensor-network-based quantum software framework
Automatic Options Hedging and Backtesting
A minimal OpenCL, CUDA, Vulkan and host CPU array manipulation engine / framework.
Error propagation and statistical analysis for Monte Carlo simulations in lattice QCD and statistical mechanics using autograd.
Keras-like APIs for JAX framework
A Fortran-based neural network library for physics-based applications. Alongside standard neural network layer types, it also supports graph-based layers and physics informed neural networks.
RusTorch is a production-grade deep learning framework re-imagined in Rust. It combines the usability you love from PyTorch with the performance, safety, and concurrency guarantees of Rust. Say goodbye to GIL locks, GC pauses, and runtime errors. Say hello to RusTorch.
Complement the article 'Differential Machine Learning' (Huge & Savine, 2020), including mathematical proofs and important implementation details for production
A numerical optimisation and deep learning framework for D.
Fast Risks with QuantLib in Python
PyRedukti is a Python library for Interest Rate Swaps and Fras, supports bootstrapping of Interest Rate Curves, computing NPV and sensitivities using automatic/algorithmic differentiation. It wraps the OpenRedukti library.
OpenRedukti is a C++ library for Interest Rate Swaps and Fras, supports bootstrapping of Interest Rate Curves, computing NPV and sensitivities using automatic/algorithmic differentiation. It provides a scripting environment in Python and Ravi (a Lua dialect).