org.deeplearning4j.nn.params

Class GravesLSTMParamInitializer

java.lang.Object

org.deeplearning4j.nn.params.GravesLSTMParamInitializer

All Implemented Interfaces:

ParamInitializer

public class GravesLSTMParamInitializer
extends java.lang.Object
implements ParamInitializer

LSTM Parameter initializer, for LSTM based on Graves: Supervised Sequence Labelling with Recurrent Neural Networks http://www.cs.toronto.edu/~graves/phd.pdf

Field Summary

Fields

Modifier and Type	Field and Description
static java.lang.String	BIAS_KEY
static java.lang.String	INPUT_WEIGHT_KEY
static java.lang.String	RECURRENT_WEIGHT_KEY Weights for previous time step -> current time step connections

Constructor Summary

Constructors

Constructor and Description
GravesLSTMParamInitializer()

Method Summary

Modifier and Type	Method and Description
java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>	getGradientsFromFlattened(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray gradientView) Return a map of gradients (in their standard non-flattened representation), taken from the flattened (row vector) gradientView array.
static GravesLSTMParamInitializer	getInstance()
java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>	init(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray paramsView, boolean initializeParams) Initialize the parameters
int	numParams(NeuralNetConfiguration conf)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

RECURRENT_WEIGHT_KEY

public static final java.lang.String RECURRENT_WEIGHT_KEY

Weights for previous time step -> current time step connections

See Also:

Constant Field Values

BIAS_KEY

public static final java.lang.String BIAS_KEY

See Also:

Constant Field Values

INPUT_WEIGHT_KEY

public static final java.lang.String INPUT_WEIGHT_KEY

See Also:

Constant Field Values

Constructor Detail

GravesLSTMParamInitializer

public GravesLSTMParamInitializer()

Method Detail

getInstance

public static GravesLSTMParamInitializer getInstance()

numParams

public int numParams(NeuralNetConfiguration conf)

Specified by:

numParams in interface ParamInitializer

init

public java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> init(NeuralNetConfiguration conf,
                                                                                 org.nd4j.linalg.api.ndarray.INDArray paramsView,
                                                                                 boolean initializeParams)

Description copied from interface: ParamInitializer

Initialize the parameters

Specified by:

init in interface ParamInitializer

Parameters:

conf - the configuration

paramsView - a view of the full network (backprop) parameters

initializeParams - if true: initialize the parameters according to the configuration. If false: don't modify the values in the paramsView array (but do select out the appropriate subset, reshape etc as required)

Returns:

Map of parameters keyed by type (view of the 'paramsView' array)

getGradientsFromFlattened

public java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> getGradientsFromFlattened(NeuralNetConfiguration conf,
                                                                                                      org.nd4j.linalg.api.ndarray.INDArray gradientView)

Description copied from interface: ParamInitializer

Return a map of gradients (in their standard non-flattened representation), taken from the flattened (row vector) gradientView array. The idea is that operates in exactly the same way as the the paramsView does in #init(Map, NeuralNetConfiguration, INDArray); thus the position in the view (and, the array orders) must match those of the parameters

Specified by:

getGradientsFromFlattened in interface ParamInitializer

Parameters:

conf - Configuration

gradientView - The flattened gradients array, as a view of the larger array

Returns:

A map containing an array by parameter type, that is a view of the full network gradients array