anny
anny copied to clipboard
levithomason
Anny is an artificial neural network, yo!
# WIP This PR will add the ability to add layers and neurons. The end goal here is to be able to visually design a network in the app.
Currently, tests are embarrassingly run with no mocks. All unit tests are actually system tests. This means most of the coverage info is exaggerated. - [ ] Add mocks for...
Simply `_.shuffle` the training data samples before training. Especially when using sorted training data, this will result in much better training results.
Currently, when a Neuron `connect()`s to another, the connection weight can be set. If there is no connection weight specified, random weight initialization is performed based on the number of...
Currently the Neuron.train() method uses the Neuron's error to calculate the delta (used to calculate the gradient and update the weights). This works OK for toy networks with a single...
Currently there is an activation namespace. Its members are activation function definitions. These are objects with `func`, `prime`, `rangeMin`, and `rangeMax` properties. These objects should be created by a class...
Just as with Neuron activations in #88, there are Network error functions in an ERROR namespace. We should do the same thing and pull these into a class or factory....
As of #83, activation ranges are now specified for all activation functions. Using this we can now scale and translate the training data to the optimal range for the activation...
Ref RProp benchmarks found in this paper. http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=298623&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D298623
Currently, the repo is used to host on gh-pages. This is causing pains by having to ignore dist files, then force add them on the CI process. The master branch...