*Ru*by *Ne*ural *Ne*tworks.
Please note this gem is effectively abandoned before any first version was published.
The proto-gem code is being left online for reference. It is MIT licensed, so anyone is free to fork it or to just take code snippets and use in their own projects.
If you are looking for a neural-network library, you have a few better choices than attempting to complete this unfinished gem. Here are some:
ruby-fann gem. The FANN library is somewhat behind on new developments in deep networks, but is perfectly servicable for small-to-medium two or three layer feed-forward networks.
Learn enough Python to use one of the many great options in that language, such as Keras. Python has far better machine learning libraries than Ruby, and will likely continue to do so for many years.
- Uses NArray sfloat arrays to represent inputs, outputs and weights.
Add this line to your application's Gemfile:
And then execute:
Or install it yourself as:
$ gem install ru_ne_ne
- Fork it
- Create your feature branch (
git checkout -b my-new-feature)
- Commit your changes (
git commit -am 'Add some feature')
- Push to the branch (
git push origin my-new-feature)
- Create new Pull Request