Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Source-to-Source Debuggable Derivatives in Pure Python
automatic differentiation made easier for C++
Deep learning in Rust, with shape checked tensors and neural networks
End-to-end Generative Optimization for AI Agents
Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.
DiffSharp: Differentiable Functional Programming
Fast, easy automatic differentiation in C++
AutoBound automatically computes upper and lower bounds on functions.
Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization
Nabla: High-Performance Scientific Computing
An interface to various automatic differentiation backends in Julia.
A JIT compiler for hybrid quantum programs in PennyLane
Drop-in autodiff for NumPy.
Autodifferentiation package in Rust.
[Experimental] Graph and Tensor Abstraction for Deep Learning all in Common Lisp
Automatic differentiation of implicit functions
High-Performance LISP-like language for Scientific Computing and AI written in C++