./math/py-autograd, Efficiently computes derivatives of numpy code

[ CVSweb ] [ Homepage ] [ RSS ] [ Required by ] [ Add to tracker ]

Branch: pkgsrc-2016Q3, Version: 1.1.5, Package name: py27-autograd-1.1.5, Maintainer: pkgsrc-users

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 uses reverse-mode differentiation
(a.k.a. backpropagation), which means it can efficiently take
gradients of scalar-valued functions with respect to array-valued
arguments. The main intended application is gradient-based
optimization.


Required to run:
[math/py-numpy]

Master sites:

SHA1: 1ed7727ac1d634b47b9ebe7244a851e76e3edd81
RMD160: 27ae3c0ef6a69141c1dddaa5975640f35ad63d94
Filesize: 24.4 KB

Version history: (Expand)