lnsc.lstm
Class FastLSTMNetwork

java.lang.Object
  |
  +--lnsc.pmvf.AbstractFunctionalUnit2
        |
        +--lnsc.lstm.FastLSTMNetwork

All Implemented Interfaces:

java.lang.Cloneable, FunctionalUnit, FunctionalUnit2, java.io.Serializable

Direct Known Subclasses:

ETLSTMNetwork1

public class FastLSTMNetwork

extends AbstractFunctionalUnit2

Long Short-Term Memory (LSMT) network.

Implements Gers, Schraudolph & Schmiduber 2002 (from Journal of Machine Learning Research 3:115-143) LSTM network. See also Gers, Schmidhuber, & Cummins 2000 (from Neural Computation, 12(10) 2451-2471) and Hochreiter & Schmidhuber 1997 (from Neural Computation 9(8):1735-1780).

This network memory reads the inputs, pass them through a layer of memory blocks, and weights memory blocks output before applying a layer of output units (usually sigmoidal). Eventually it may support hidden units (trainable using truncated gradient). The memory blocks are fully recurrently connected. The input are expendend with a bias unit to feed the memory block. The parameters are all the weights feeding the memory block (foward and recurrent) and the weights feeding the output layer. Output layer can be feed by everything (bias, input, memory block outputs, memory block gates). Gradient from network output to all the weights is provided as in the paper. Only derivatives to these parameters is available.

Parameters are all the weights of the memory blocks and all the weights of the output layer. Derivative to parameters represent the derivative of each output z_k(t) with respect to each weights based on the papers formulas.

Memory cells internal states, outputs, and memory block gates are available through keywords in LSTMDataNames.

Cloning is done through serialization, transient states are therefore transient to cloning too (e.g. reseted in clones).

Avoid using this class directly or deriving it unless you really know what you do. Use Factories instead as much as possible.

Since:

1.0

See Also:

FastLSTMMemoryBlock, AbstractLSTMFactory, LSTMFactory, LSTMDataNames, Serialized Form

Nested Class Summary

Nested classes inherited from class lnsc.pmvf.FunctionalUnit2

FunctionalUnit2.ProcessPatternResult2

Nested classes inherited from class lnsc.FunctionalUnit

FunctionalUnit.ProcessPatternResult

Field Summary

boolean

m_Debug Public debug info output.

Fields inherited from interface lnsc.FunctionalUnit

EMPTY_PATTERN

Method Summary

java.lang.Object	clone()
double[]	getParameters() Gets a copy of the parameters as a vector.
FunctionalUnit2.ProcessPatternResult2	processPattern(double[] inputPattern, boolean computeDerivative, boolean computeSecondDerivative, boolean computeParameterDerivative, boolean computeParameterSecondDerivative, java.lang.String[] recordList) Processes an input pattern and returns its output pattern and derivatives (if requested).
void	reset() Reset internal transient state for non stateless functions.
void	setParameters(double[] parameters) Sets the parameters values to those of a given vector.
java.lang.String	toString()

Methods inherited from class lnsc.pmvf.AbstractFunctionalUnit2

getInputCount, getOutputCount, getParameterCount, isDifferentiable, isParameterDifferentiable, isParameterTwiceDifferentiable, isStateless, isTwiceDifferentiable, processDataSet, processPattern

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

m_Debug

public boolean m_Debug

Public debug info output.

Method Detail

clone

public java.lang.Object clone()

Specified by:

clone in interface FunctionalUnit

Overrides:

clone in class AbstractFunctionalUnit2

getParameters

public double[] getParameters()

Description copied from interface: FunctionalUnit2

Gets a copy of the parameters as a vector.

Returns:

A copy of the parameter values.

processPattern

public FunctionalUnit2.ProcessPatternResult2 processPattern(double[] inputPattern,
                                                            boolean computeDerivative,
                                                            boolean computeSecondDerivative,
                                                            boolean computeParameterDerivative,
                                                            boolean computeParameterSecondDerivative,
                                                            java.lang.String[] recordList)

Description copied from interface: FunctionalUnit2

Processes an input pattern and returns its output pattern and derivatives (if requested).

Specified by:

processPattern in interface FunctionalUnit2

Overrides:

processPattern in class AbstractFunctionalUnit2

Parameters:

inputPattern - The input pattern.

computeDerivative - Must be true if the derivative should be computed.

computeSecondDerivative - Must be true if the second derivative should be computed.

computeParameterDerivative - Must be true if the derivative with respect to the parameters should be computed.

computeParameterSecondDerivative - Must be true if be the derivative with respect to the parameters should be computed.

recordList - Extra data to be recorded.

Returns:

The output pattern and the derivative (if requested).

reset

public void reset()

Description copied from interface: FunctionalUnit

Reset internal transient state for non stateless functions.

Specified by:

reset in interface FunctionalUnit

Overrides:

reset in class AbstractFunctionalUnit2

setParameters

public void setParameters(double[] parameters)

Description copied from interface: FunctionalUnit2

Sets the parameters values to those of a given vector.

toString

public java.lang.String toString()

Overrides:

toString in class AbstractFunctionalUnit2