Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

Source-to-Source Debuggable Derivatives in Pure Python

Deep learning in Rust, with shape checked tensors and neural networks

automatic differentiation made easier for C++

Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.

DiffSharp: Differentiable Functional Programming

Assignment 1: automatic differentiation

End-to-end Generative Optimization for AI Agents

AutoBound automatically computes upper and lower bounds on functions.

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

An interface to various automatic differentiation backends in Julia.

Drop-in autodiff for NumPy.

Autodifferentiation package in Rust.

A JIT compiler for hybrid quantum programs in PennyLane

[Experimental] Graph and Tensor Abstraction for Deep Learning all in Common Lisp

Automatic differentiation of implicit functions

Tensors and dynamic Neural Networks in Mojo

An experimental deep learning framework for Nim based on a differentiable array programming language

Minimal deep learning library written from scratch in Python, using NumPy/CuPy.