Py-autograd

Jul 20, 2023

Efficiently computes derivatives of numpy code

Autograd can automatically differentiate native Python and Numpy code. It can handle a large subset of Python’s features, including loops, ifs, recursion and closures, and it can even take derivatives of derivatives of derivatives. It supports reverse-mode differentiation a.k.a. backpropagation, which means it can efficiently take gradients of scalar-valued functions with respect to array-valued arguments, as well as forward-mode differentiation, and the two can be composed arbitrarily. The main intended application of Autograd is gradient-based optimization.



Checkout these related ports:
  • Zn_poly - C library for polynomial arithmetic
  • Zimpl - Language to translate the LP models into .lp or .mps
  • Zegrapher - Software for plotting mathematical objects
  • Zarray - Dynamically typed N-D expression system based on xtensor
  • Z3 - Z3 Theorem Prover
  • Yices - SMT solver
  • Yacas - Yet Another Computer Algebra System
  • Xtensor - Multi-dimensional arrays with broadcasting and lazy computing
  • Xtensor-python - Python bindings for xtensor
  • Xtensor-io - Xtensor plugin to read/write images, audio files, numpy npz and HDF5
  • Xtensor-blas - BLAS extension to xtensor
  • Xspread - Spreadsheet program for X and terminals
  • Xppaut - Graphical tool for solving differential equations, etc
  • Xplot - X11 plotting package
  • Xlife++ - XLiFE++ eXtended Library of Finite Elements in C++