ml-fnn

Feedforward Neural Network

A implementation of feedforward neural networks in javascript based on the mrbo answer found here:

[Implementation] (http://stackoverflow.com/questions/9951487/implementing-a-neural-network-in-java-training-and-backpropagation-issues)

Methods

new FeedforwardNeuralNetwork([LayersSize])

Arguments

• layersSize - Array of numbers with sizes of each layer.

Example

var FNN = new FeedforwardNeuralNetwork([2, 4, 1]);

train(trainingSet, predictions, learningRate, momentum)

Train the Neural Network with a given training set, predictions, learning rate and a momentum (Regularization term).

Arguments

• trainingSet - A matrix of the training set.
• predictions - A matrix of predictions with the same size of rows of the trainingSet.
• learningRate - The learning rate (number).
• momentum - The regularization term (number).

Example

var trainingSet = [[0, 0], [0, 1], [1, 0], [1, 1]];
var predictions = [[0], [0], [0], [1]];

FNN.train(trainingSet, predictions, 0.3, 0.3);

predict(dataset)

Predict the values of the dataset.

Arguments

• dataset - A matrix that contains the dataset.

Example

var dataset = [[0, 0], [0, 1], [1, 0], [1, 1]];

var ans = FNN.predict(dataset);

export()

Exports the actual Neural Network to an Javascript Object.

load(model)

Returns a new Neural Network with the given model.

Arguments

• model - Javascript Object generated from export() function.

Authors

• Jefferson Hernandez

License

MIT