A simple automatic differentiation library in Rust.
-
Updated
Mar 3, 2023 - Rust
A simple automatic differentiation library in Rust.
A dual number type for automatic differentiation.
A pedagogical implementation of Automatic Differation on multi-dimensional tensors.
AD with Enzyme through Lulesh.
Gograd is a small automatic differentiation framework written in Go.
A simple forward mode automatic differentiation package
PyTorch Autodiff DFT-D4 Implementation.
python implementation of automatic differentiation for functions written in vanilla python or numpy
This library provides expression trees for representation of geometric expressions and automatic differentiation of these expressions. This enables to write down geometric expressions at the position level, and automatically compute Jacobians and higher order derivatives efficiently and without loss of precision. The library is built upon the KD…
Solving Schrodinger's Equation with a Neural Network using numerical integration and autograd. Check https://arxiv.org/abs/2104.04795
Domain Specific Language to perform Automatic Differentiation on Higher Order functions.
Provides an implementation of a missing primitive in JAX, value_and_jacfwd
Numerical Algorithms and Their Implementation
Solution of Simply Supported Rectangular Plates under Sinusoidal Load using Automatic Differentiation
Simple Deep Learning library in Rust based on ndarray.
Derivatives (mathematical) computation tools
A minimal example of reverse-mode automatic differentiation (aka backpropagation)
Slides in reveal.js, covering an introduction to PyTorch
An Implementation of Generalized Dual Numbers
Arduino based Automatic Measurement System that can measure voltage and current in the ranges: {-500mV... +500mV}, {-5V... +5V} (changeable)
Add a description, image, and links to the automatic-differentiation topic page so that developers can more easily learn about it.
To associate your repository with the automatic-differentiation topic, visit your repo's landing page and select "manage topics."