Package crino :: Module network :: Class DeepNeuralNetwork

[frames] | no frames]

Class DeepNeuralNetwork

A DeepNeuralNetwork (DNN) is a specialization of the MLP, where the layers are pretrained on the training examples (x)usingaStacked strategy. It has been specifically designed for data that lies in a high-dimensional input space.

See Also: MultiLayerPerceptron, http://www.deeplearning.net/tutorial/SdA.html

Instance Methods

__init__(self, nUnitsInput, nUnitsOutput, outputActivation=<class crino.module.Sigmoid at 0x2b85740f5db8>)
Constructs a new DeepNeuralNetwork.

source code

Inherited from PretrainedMLP: prepareParams, pretrainInputAutoEncoders, pretrainOutputAutoEncoders, train

Inherited from MultiLayerPerceptron: checkBadmoveHook, checkBatchHook, checkEpochHook, checkLearningParameters, defaultLearningParameters, finetune, getGeometry, getParameters, initBadmoveHook, initBatchHook, initEpochHook, setParameters

Inherited from module.Sequential: prepareGeometry, prepareOutput

Inherited from module.Container: add

Inherited from module.Module: criterionFunction, forward, forwardFunction, holdFunction, linkInputs, linkModule, prepare, prepareBackup, restoreFunction, save, trainFunction

Instance Variables

Inherited from module.Container: modules

Inherited from module.Module: backupParams, inputs, nInputs, nOutputs, outputs, params, prepared

Method Details

init(self, nUnitsInput, nUnitsOutput, outputActivation=<class crino.module.Sigmoid at 0x2b85740f5db8>)
(Constructor)

Constructs a new DeepNeuralNetwork.

Parameters:

nUnitsInput (int list) - The sizes of the (input and hidden) representations on the input side.
nUnitsOutput (int list) - The sizes of the (hidden and output) representations on the output side.
outputActivation (class derived from Activation) - The type of activation for the output layer.

Overrides: module.Module.__init__

Attention: outputActivation parameter is not an instance but a class.