| Name : python3-autograd
| |
| Version : 1.3
| Vendor : Fedora Project
|
| Release : 13.fc35
| Date : 2022-02-15 13:04:29
|
| Group : Unspecified
| Source RPM : python-autograd-1.3-13.fc35.src.rpm
|
| Size : 0.40 MB
| |
| Packager : Fedora Project
| |
| Summary : 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.
|
RPM found in directory: /packages/linux-pbone/archive.fedoraproject.org/fedora-secondary/updates/35/Everything/ppc64le/Packages/p |
