SGDNetworkTrainer (Java Statistical Analysis Tool 0.0.8 API)

java.lang.Object
- jsat.classifiers.neuralnetwork.SGDNetworkTrainer

All Implemented Interfaces:

Serializable
```
public class SGDNetworkTrainer
extends Object
implements Serializable
```
This class provides a highly configurable and generalized method of training a neural network using Stochastic Gradient Decent.

Note, the API of this class may change in the future.

Author:

Edward Raff

See Also:

Serialized Form

Constructor Summary

Constructors
Constructor and Description

SGDNetworkTrainer()
Creates a new SGD network training that uses dropout

SGDNetworkTrainer(SGDNetworkTrainer toCopy)
Copy constructor

Constructors
Constructor and Description
`SGDNetworkTrainer()` Creates a new SGD network training that uses dropout
`SGDNetworkTrainer(SGDNetworkTrainer toCopy)` Copy constructor

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`protected SGDNetworkTrainer`	`clone()`
`Vec`	`feedfoward(Vec x)` Feeds the given singular pattern through the network and computes its activations
`void`	`finishUpdating()` Calling this method indicates that the user has no intentions of updating the network again and is ready to use it for prediction.
`BiastInitializer`	`getBiasInit()`
`double`	`getDropoutHidden()`
`double`	`getDropoutInput()`
`double`	`getEta()`
`DecayRate`	`getEtaDecay()`
`GradientUpdater`	`getGradientUpdater()`
`int[]`	`getLayerSizes()`
`WeightRegularizer`	`getRegularizer()`
`WeightInitializer`	`getWeightInit()`
`void`	`setBiasInit(BiastInitializer biasInit)` Sets the method to use when initializing neuron bias values
`void`	`setDropoutHidden(double p)` Sets the probability of dropping a value from the hidden layer
`void`	`setDropoutInput(double p)` Sets the probability of dropping a value from the input layer
`void`	`setEta(double eta)` Sets the base global learning rate.
`void`	`setEtaDecay(DecayRate etaDecay)` Sets the decay rate on the global learning rate over time
`void`	`setGradientUpdater(GradientUpdater updater)` Sets the gradient update that will be used when updating the weight matrices and bias terms.
`void`	`setLayersActivation(List<ActivationLayer> layersActivation)` Sets the list of layer activations for all layers other than the input layer.
`void`	`setLayerSizes(int... layerSizes)` Sets the array indicating the total number of layers in the network and the sizes of each layer.
`void`	`setRegularizer(WeightRegularizer regularizer)` Sets the method of regularizing the connections weights
`void`	`setup()` Prepares the network by creating all needed structure, initializing weights, and preparing it for updates
`void`	`setWeightInit(WeightInitializer weightInit)` Sets the method used to initialize matrix connection weights
`double`	`updateMiniBatch(List<Vec> x, List<Vec> y)` Performs a mini-batch update of the network using the given input and output pairs
`double`	`updateMiniBatch(List<Vec> x, List<Vec> y, ExecutorService ex)` Performs a mini-batch update of the network using the given input and output pairs

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - SGDNetworkTrainer
```
public SGDNetworkTrainer()
```
    Creates a new SGD network training that uses dropout
  - SGDNetworkTrainer
```
public SGDNetworkTrainer(SGDNetworkTrainer toCopy)
```
    Copy constructor
    
    Parameters:
    
    toCopy - the object to copy
- Method Detail
  - setDropoutInput
```
public void setDropoutInput(double p)
```
    Sets the probability of dropping a value from the input layer
    
    Parameters:
    
    p - the probability in [0, 1) of dropping a value in the input layer
  - getDropoutInput
```
public double getDropoutInput()
```
    Returns:
    
    the dropout probability for the input layer
  - setDropoutHidden
```
public void setDropoutHidden(double p)
```
    Sets the probability of dropping a value from the hidden layer
    
    Parameters:
    
    p - the probability in [0, 1) of dropping a value in the hidden layer
  - getDropoutHidden
```
public double getDropoutHidden()
```
    Returns:
    
    the dropout probability for the hidden layers
  - setEtaDecay
```
public void setEtaDecay(DecayRate etaDecay)
```
    Sets the decay rate on the global learning rate over time
    
    Parameters:
    
    etaDecay - the decay rate to use
  - getEtaDecay
```
public DecayRate getEtaDecay()
```
    Returns:
    
    the decay rate in use
  - setEta
```
public void setEta(double eta)
```
    Sets the base global learning rate.
    
    Parameters:
    
    eta - the learning rate to use
  - getEta
```
public double getEta()
```
    Returns:
    
    the global learning rate used
  - setRegularizer
```
public void setRegularizer(WeightRegularizer regularizer)
```
    Sets the method of regularizing the connections weights
    
    Parameters:
    
    regularizer - the method of regularizing the network
  - getRegularizer
```
public WeightRegularizer getRegularizer()
```
    Returns:
    
    the regularizer for the network
  - setLayerSizes
```
public void setLayerSizes(int... layerSizes)
```
    Sets the array indicating the total number of layers in the network and the sizes of each layer. The length of the array is the number of layers and the value at each index is the size of that layer.
    
    Parameters:
    
    layerSizes - the array of layer sizes
  - getLayerSizes
```
public int[] getLayerSizes()
```
    Returns:
    
    the array of layer sizes in the network
  - setLayersActivation
```
public void setLayersActivation(List<ActivationLayer> layersActivation)
```
    Sets the list of layer activations for all layers other than the input layer.
    
    Parameters:
    
    layersActivation - the list of hidden and output layer activations
  - setGradientUpdater
```
public void setGradientUpdater(GradientUpdater updater)
```
    Sets the gradient update that will be used when updating the weight matrices and bias terms.
    
    Parameters:
    
    updater - the updater to use
  - getGradientUpdater
```
public GradientUpdater getGradientUpdater()
```
    Returns:
    
    the gradient updater used
  - setWeightInit
```
public void setWeightInit(WeightInitializer weightInit)
```
    Sets the method used to initialize matrix connection weights
    
    Parameters:
    
    weightInit - the weight initialization method
  - getWeightInit
```
public WeightInitializer getWeightInit()
```
    Returns:
    
    the weight initialization method
  - setBiasInit
```
public void setBiasInit(BiastInitializer biasInit)
```
    Sets the method to use when initializing neuron bias values
    
    Parameters:
    
    biasInit - the bias initialization method
  - getBiasInit
```
public BiastInitializer getBiasInit()
```
    Returns:
    
    the bias initialization method
  - setup
```
public void setup()
```
    Prepares the network by creating all needed structure, initializing weights, and preparing it for updates
  - finishUpdating
```
public void finishUpdating()
```
    Calling this method indicates that the user has no intentions of updating the network again and is ready to use it for prediction. This will remove objects not needed for prediction and do cleanup.
  - updateMiniBatch
```
public double updateMiniBatch(List<Vec> x,
                              List<Vec> y)
```
    Performs a mini-batch update of the network using the given input and output pairs
    
    Parameters:
    
    x - the list of input values
    
    y - the list of output values
    
    Returns:
    
    the error incurred on the given mini batch
  - updateMiniBatch
```
public double updateMiniBatch(List<Vec> x,
                              List<Vec> y,
                              ExecutorService ex)
```
    Performs a mini-batch update of the network using the given input and output pairs
    
    Parameters:
    
    x - the list of input values
    
    y - the list of output values
    
    ex - the source of threads for parallel computation, may be null
    
    Returns:
    
    the error incurred on the given mini batch
  - feedfoward
```
public Vec feedfoward(Vec x)
```
    Feeds the given singular pattern through the network and computes its activations
    
    Parameters:
    
    x - the input vector to feed forward through the network
    
    Returns:
    
    the final activation for this network
  - clone
```
protected SGDNetworkTrainer clone()
```
    Overrides:
    
    clone in class Object

Class SGDNetworkTrainer

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

SGDNetworkTrainer

SGDNetworkTrainer

Method Detail

setDropoutInput

getDropoutInput

setDropoutHidden

getDropoutHidden

setEtaDecay

getEtaDecay

setEta

getEta

setRegularizer

getRegularizer

setLayerSizes

getLayerSizes

setLayersActivation

setGradientUpdater

getGradientUpdater

setWeightInit

getWeightInit

setBiasInit

getBiasInit

setup

finishUpdating

updateMiniBatch

updateMiniBatch

feedfoward

clone