C++20 machine learning library with no external dependencies (nanorange used temporarily for C++20 ranges)
-
Updated
Oct 13, 2019 - C++
C++20 machine learning library with no external dependencies (nanorange used temporarily for C++20 ranges)
Reversed mode second order automatic differentiation for python (WIP)
MicrogradPlus is an educational project aiming to provide a simple, yet extensible, NumPy-based automatic differentiation library.
A framework for more flexible structure of neural networks with auto-differentiation.
Define-by-run arbitrary higher order autodiff for scalars in Rust. Deferred: tensor calculus implementation.
MetaAutoDiff is a C++ template library for automatic differentiation in reverse mode.
autoD is a lightweight, flexible automatic differentiation for python3 based on numpy.
Lagrangian mechanics implemented 3 ways: manually, with auto-diff, and symbolically.
MinimalGrad is an open-source automatic differentiation library for deep learning that is designed to be lightweight and efficient, with a focus on simplicity and ease of use. It was developed by a team of students at Eötvös Loránd University as part of Advanced software technology class.
A fast auto differentiation engine implemented in C++ 🔥
🎈 A C++ code generator for the automatic derivation of tensors with linear indexes. Implementation for the lesson Compiling Technology(2020 Spring, advised by Yun Liang) in Peking University.
Neural Network library made with numpy
Differentiable tensor renormalization group
Automatic derivative calculation of scalar functions.
Fortran backward (reverse) mode automatic differentiation.
A WIP library for performing multi-root searching of one-dimensional transcendental equations using auto-differentiation in Rust
Calculates partial derivatives of an input function.
Tiny calculation graph library
Add a description, image, and links to the auto-differentiation topic page so that developers can more easily learn about it.
To associate your repository with the auto-differentiation topic, visit your repo's landing page and select "manage topics."