gaunn

Lib

Project description

This contains Feedforward and Recurrent neural networks

Feedforward and Recurrent neural nets
Contains logistic, tanh, ReLU, softmax neurons
Standard loss functions (squared error, cross entropy, sparsity constraints), and support for custom loss functions
Different methods to initialize weights
Customizable connectivity between layers
Inputs can be generated dynamically by some other system (like a simulation)

Install the package via:

pip install gaunn

This version

1.0.0

Aug 30, 2016

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Uploaded Aug 30, 2016 Source

Uploaded Aug 30, 2016 Python 2

Hashes for gaunn-1.0.0.tar.gz
Algorithm	Hash digest
SHA256	`30d0320301bbdafbd24647f4eadea737a53341ed8d03b8420bb09dac9460d3d8`
MD5	`f2f93caa3869cb86ba71d83508c0471b`
BLAKE2b-256	`0ec8d5a040c7a94ea4654eea7f169248a67c2d380788410a8f87767c5853df16`

Hashes for gaunn-1.0.0-py2-none-any.whl
Algorithm	Hash digest
SHA256	`1de6b484362b25962fd5f3d7e9276a54237b2794a7bcd208ad9603821c0c9e71`
MD5	`3fc861f382306db802c519eb203ab240`
BLAKE2b-256	`fd64b17bb8123619f50069d8c51384a4a086fc7b93f7e5aaefdd0c8f56eb80fd`