Package hex.deeplearning

Interface Summary

Interface	Description
Neurons.Matrix	Abstract matrix interface
Neurons.Vector	Abstract vector interface

Class Summary

Class	Description
DeepLearning	Deep Learning Neural Net implementation based on MRTask2
DeepLearningModel	The Deep Learning model It contains a DeepLearningModelInfo with the most up-to-date model, a scoring history, as well as some helpers to indicated the progress
DeepLearningModel.DeepLearningModelInfo
DeepLearningModel.Errors
DeepLearningTask
DeepLearningTask2	DRemoteTask-based Deep Learning.
Dropout	Helper class for dropout training of Neural Nets
Neurons	This class implements the concept of a Neuron layer in a Neural Network During training, every MRTask2 F/J thread is expected to create these neurons for every map call (Cheap to make).
Neurons.DenseColMatrix	Dense column matrix implementation
Neurons.DenseRowMatrix	Dense row matrix implementation
Neurons.DenseVector	Dense vector implementation
Neurons.Input	Input layer of the Neural Network This layer is different from other layers as it has no incoming weights, but instead gets its activation values from the training points.
Neurons.Linear	Output neurons for regression - Softmax
Neurons.Maxout	Maxout neurons
Neurons.MaxoutDropout	Maxout neurons with dropout
Neurons.Output	Abstract class for Output neurons
Neurons.Rectifier	Rectifier linear unit (ReLU) neurons
Neurons.RectifierDropout	Rectifier linear unit (ReLU) neurons with dropout
Neurons.Softmax	Output neurons for classification - Softmax
Neurons.SparseRowMatrix	Sparse row matrix implementation
Neurons.SparseVector	Sparse vector implementation
Neurons.Tanh	Tanh neurons - most common, most stable
Neurons.TanhDropout	Tanh neurons with dropout

Enum Summary

Enum	Description
DeepLearning.Activation	Activation functions
DeepLearning.ClassSamplingMethod
DeepLearning.InitialWeightDistribution
DeepLearning.Loss	Loss functions CrossEntropy is recommended