Language

Package: python-autograd @ 0.0.0-0.442205d

Synopsis

Efficiently computes derivatives of NumPy code

Description

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.

Home page
https://github.com/HIPS/autograd
Location
gnu/packages/machine-learning.scm (line: 1331, column: 4)
License

Lint warnings

LinterMessageLocation
optional-tests

Make sure tests are only run when requested

the 'check' phase should respect #:tests?