diff options
author | Ruslan Makhmatkhanov <rm@FreeBSD.org> | 2019-02-27 22:11:15 +0000 |
---|---|---|
committer | Ruslan Makhmatkhanov <rm@FreeBSD.org> | 2019-02-27 22:11:15 +0000 |
commit | edc98fd01e771202aa5b15b23421e6318f37f156 (patch) | |
tree | c33c1e687df9a895b5ee28da9c42dd5d0af5a6cd /math/Makefile | |
parent | c7f0ef2cc127ee95eddaf51262de00291cb8391d (diff) | |
download | ports-edc98fd01e771202aa5b15b23421e6318f37f156.tar.gz ports-edc98fd01e771202aa5b15b23421e6318f37f156.zip |
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.
WWW: https://github.com/HIPS/autograd
Notes
Notes:
svn path=/head/; revision=494091
Diffstat (limited to 'math/Makefile')
-rw-r--r-- | math/Makefile | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/math/Makefile b/math/Makefile index 815b23289681..4689fbe81a6e 100644 --- a/math/Makefile +++ b/math/Makefile @@ -690,6 +690,7 @@ SUBDIR += py-algopy SUBDIR += py-altgraph SUBDIR += py-apgl + SUBDIR += py-autograd SUBDIR += py-basemap SUBDIR += py-basemap-data SUBDIR += py-bayesian-optimization |