A small basic neural network package
Project description
Luparnet
**Luparnet** is a barebones machine learning that creates a simple class "net". This
network can then be trained.
Methods
The network takes only two arguments in the constructor, the first being
the desired number of layers and the second being an array of the data dimensions. The train function takes three arguments with an option for overload. The function takes first the number of epochs to train for, the second is the input data, the third is the output data. The final argument is an integer which allows for debugging and user training.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
luparnet-0.1.1.tar.gz
(1.4 kB
view hashes)