NeuralNetConfiguration.Builder (deeplearning4j-nn 0.9.1 API)

java.lang.Object
- org.deeplearning4j.nn.conf.NeuralNetConfiguration.Builder

All Implemented Interfaces:: Cloneable

Enclosing class:: NeuralNetConfiguration

public static class NeuralNetConfiguration.Builder
extends Object
implements Cloneable

Field Summary

Fields
Modifier and Type	Field and Description
`protected org.nd4j.linalg.activations.IActivation`	`activationFn`
`protected double`	`adamMeanDecay` Deprecated.
`protected double`	`adamVarDecay` Deprecated.
`protected double`	`biasInit`
`protected double`	`biasLearningRate`
`protected CacheMode`	`cacheMode`
`protected ConvolutionMode`	`convolutionMode`
`protected Distribution`	`dist`
`protected double`	`dropOut`
`protected double`	`epsilon` Deprecated.
`protected GradientNormalization`	`gradientNormalization`
`protected double`	`gradientNormalizationThreshold`
`protected WorkspaceMode`	`inferenceWorkspaceMode`
`protected org.nd4j.linalg.learning.config.IUpdater`	`iUpdater`
`protected double`	`l1`
`protected double`	`l1Bias`
`protected double`	`l2`
`protected double`	`l2Bias`
`protected Layer`	`layer`
`protected double`	`leakyreluAlpha` Deprecated.
`protected double`	`learningRate`
`protected LearningRatePolicy`	`learningRatePolicy`
`protected Map<Integer,Double>`	`learningRateSchedule`
`protected double`	`lrPolicyDecayRate`
`protected double`	`lrPolicyPower`
`protected double`	`lrPolicySteps`
`protected double`	`lrScoreBasedDecay`
`protected int`	`maxNumLineSearchIterations`
`protected boolean`	`miniBatch`
`protected boolean`	`minimize`
`protected double`	`momentum` Deprecated.
`protected Map<Integer,Double>`	`momentumSchedule` Deprecated.
`protected int`	`numIterations`
`protected OptimizationAlgorithm`	`optimizationAlgo`
`protected boolean`	`pretrain`
`protected double`	`rho` Deprecated.
`protected double`	`rmsDecay` Deprecated.
`protected long`	`seed`
`protected StepFunction`	`stepFunction`
`protected WorkspaceMode`	`trainingWorkspaceMode`
`protected Updater`	`updater` Deprecated.
`protected boolean`	`useDropConnect`
`protected boolean`	`useRegularization`
`protected WeightInit`	`weightInit`

Constructor Summary

Constructors
Constructor and Description

Builder()

Builder(NeuralNetConfiguration newConf)

Constructors
Constructor and Description
`Builder()`
`Builder(NeuralNetConfiguration newConf)`

Method Summary

All Methods Instance Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`NeuralNetConfiguration.Builder`	`activation(org.nd4j.linalg.activations.Activation activation)` Activation function / neuron non-linearity
`NeuralNetConfiguration.Builder`	`activation(org.nd4j.linalg.activations.IActivation activationFunction)` Activation function / neuron non-linearity
`NeuralNetConfiguration.Builder`	`activation(String activationFunction)` Deprecated. Use `activation(Activation)` or `@activation(IActivation)`
`NeuralNetConfiguration.Builder`	`adamMeanDecay(double adamMeanDecay)` Deprecated. use `.updater(Adam.builder().beta1(adamMeanDecay).build())` intead
`NeuralNetConfiguration.Builder`	`adamVarDecay(double adamVarDecay)` Deprecated. use `.updater(Adam.builder().beta2(adamVarDecay).build())` intead
`NeuralNetConfiguration.Builder`	`biasInit(double biasInit)` Constant for bias initialization.
`NeuralNetConfiguration.Builder`	`biasLearningRate(double biasLearningRate)` Bias learning rate.
`NeuralNetConfiguration`	`build()` Return a configuration based on this builder
`NeuralNetConfiguration.Builder`	`cacheMode(CacheMode cacheMode)` This method defines how/if preOutput cache is handled: NONE: cache disabled (default value) HOST: Host memory will be used DEVICE: GPU memory will be used (on CPU backends effect will be the same as for HOST)
`NeuralNetConfiguration.Builder`	`clone()`
`NeuralNetConfiguration.Builder`	`convolutionMode(ConvolutionMode convolutionMode)`
`NeuralNetConfiguration.Builder`	`dist(Distribution dist)` Distribution to sample initial weights from.
`NeuralNetConfiguration.Builder`	`dropOut(double dropOut)` Dropout probability.
`NeuralNetConfiguration.Builder`	`epsilon(double epsilon)` Deprecated. Use use `.updater(Adam.builder().epsilon(epsilon).build())` or similar instead
`NeuralNetConfiguration.Builder`	`gradientNormalization(GradientNormalization gradientNormalization)` Gradient normalization strategy.
`NeuralNetConfiguration.Builder`	`gradientNormalizationThreshold(double threshold)` Threshold for gradient normalization, only used for GradientNormalization.ClipL2PerLayer, GradientNormalization.ClipL2PerParamType, and GradientNormalization.ClipElementWiseAbsoluteValue Not used otherwise. L2 threshold for first two types of clipping, or absolute value threshold for last type of clipping.
`ComputationGraphConfiguration.GraphBuilder`	`graphBuilder()` Create a GraphBuilder (for creating a ComputationGraphConfiguration).
`NeuralNetConfiguration.Builder`	`inferenceWorkspaceMode(WorkspaceMode workspaceMode)` This method defines Workspace mode being used during inference: NONE: workspace won't be used SINGLE: one workspace will be used during whole iteration loop SEPARATE: separate workspaces will be used for feedforward and backprop iteration loops
`NeuralNetConfiguration.Builder`	`iterations(int numIterations)` Number of optimization iterations.
`NeuralNetConfiguration.Builder`	`l1(double l1)` L1 regularization coefficient for the weights.
`NeuralNetConfiguration.Builder`	`l1Bias(double l1Bias)` L1 regularization coefficient for the bias.
`NeuralNetConfiguration.Builder`	`l2(double l2)` L2 regularization coefficient for the weights.
`NeuralNetConfiguration.Builder`	`l2Bias(double l2Bias)` L2 regularization coefficient for the bias.
`NeuralNetConfiguration.Builder`	`layer(Layer layer)` Layer class.
`NeuralNetConfiguration.Builder`	`leakyreluAlpha(double leakyreluAlpha)` Deprecated. Use `activation(IActivation)` with leaky relu, setting alpha value directly in constructor.
`NeuralNetConfiguration.Builder`	`learningRate(double learningRate)` Learning rate.
`NeuralNetConfiguration.Builder`	`learningRateDecayPolicy(LearningRatePolicy policy)` Learning rate decay policy.
`NeuralNetConfiguration.Builder`	`learningRateSchedule(Map<Integer,Double> learningRateSchedule)` Learning rate schedule.
`NeuralNetConfiguration.Builder`	`learningRateScoreBasedDecayRate(double lrScoreBasedDecay)` Rate to decrease learningRate by when the score stops improving.
`NeuralNetConfiguration.ListBuilder`	`list()` Create a ListBuilder (for creating a MultiLayerConfiguration) Usage:
`NeuralNetConfiguration.ListBuilder`	`list(Layer... layers)` Create a ListBuilder (for creating a MultiLayerConfiguration) with the specified layers Usage:
`NeuralNetConfiguration.Builder`	`lrPolicyDecayRate(double lrPolicyDecayRate)` Set the decay rate for the learning rate decay policy.
`NeuralNetConfiguration.Builder`	`lrPolicyPower(double lrPolicyPower)` Set the power used for learning rate inverse policy.
`NeuralNetConfiguration.Builder`	`lrPolicySteps(double lrPolicySteps)` Set the number of steps used for learning decay rate steps policy.
`NeuralNetConfiguration.Builder`	`maxNumLineSearchIterations(int maxNumLineSearchIterations)` Maximum number of line search iterations.
`NeuralNetConfiguration.Builder`	`miniBatch(boolean miniBatch)` Process input as minibatch vs full dataset.
`NeuralNetConfiguration.Builder`	`minimize(boolean minimize)` Objective function to minimize or maximize cost function Default set to minimize true.
`NeuralNetConfiguration.Builder`	`momentum(double momentum)` Deprecated. Use `.updater(new Nesterov(momentum))` instead
`NeuralNetConfiguration.Builder`	`momentumAfter(Map<Integer,Double> momentumAfter)` Deprecated. Use `.updater(Nesterov.builder().momentumSchedule(schedule).build())` instead
`NeuralNetConfiguration.Builder`	`optimizationAlgo(OptimizationAlgorithm optimizationAlgo)` Optimization algorithm to use.
`NeuralNetConfiguration.Builder`	`regularization(boolean useRegularization)` Whether to use regularization (l1, l2, dropout, etc
`NeuralNetConfiguration.Builder`	`rho(double rho)` Deprecated. use `.updater(new AdaDelta(rho,epsilon))` intead
`NeuralNetConfiguration.Builder`	`rmsDecay(double rmsDecay)` Deprecated. use `.updater(new RmsProp(rmsDecay))` intead
`NeuralNetConfiguration.Builder`	`seed(int seed)` Random number generator seed.
`NeuralNetConfiguration.Builder`	`seed(long seed)` Random number generator seed.
`NeuralNetConfiguration.Builder`	`stepFunction(StepFunction stepFunction)` Step function to apply for back track line search.
`NeuralNetConfiguration.Builder`	`trainingWorkspaceMode(WorkspaceMode workspaceMode)` This method defines Workspace mode being used during training: NONE: workspace won't be used SINGLE: one workspace will be used during whole iteration loop SEPARATE: separate workspaces will be used for feedforward and backprop iteration loops
`NeuralNetConfiguration.Builder`	`updater(org.nd4j.linalg.learning.config.IUpdater updater)` Gradient updater.
`NeuralNetConfiguration.Builder`	`updater(Updater updater)` Gradient updater.
`NeuralNetConfiguration.Builder`	`useDropConnect(boolean useDropConnect)` Use drop connect: multiply the weight by a binomial sampling wrt the dropout probability.
`NeuralNetConfiguration.Builder`	`weightInit(WeightInit weightInit)` Weight initialization scheme.

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

- Field Detail
  - activationFn
```
protected org.nd4j.linalg.activations.IActivation activationFn
```
  - weightInit
```
protected WeightInit weightInit
```
  - biasInit
```
protected double biasInit
```
  - dist
```
protected Distribution dist
```
  - learningRate
```
protected double learningRate
```
  - biasLearningRate
```
protected double biasLearningRate
```
  - learningRateSchedule
```
protected Map<Integer,Double> learningRateSchedule
```
  - lrScoreBasedDecay
```
protected double lrScoreBasedDecay
```
  - l1
```
protected double l1
```
  - l2
```
protected double l2
```
  - l1Bias
```
protected double l1Bias
```
  - l2Bias
```
protected double l2Bias
```
  - dropOut
```
protected double dropOut
```
  - updater
```
@Deprecated
protected Updater updater
```
    Deprecated.
  - iUpdater
```
protected org.nd4j.linalg.learning.config.IUpdater iUpdater
```
  - momentum
```
@Deprecated
protected double momentum
```
    Deprecated.
  - momentumSchedule
```
@Deprecated
protected Map<Integer,Double> momentumSchedule
```
    Deprecated.
  - epsilon
```
@Deprecated
protected double epsilon
```
    Deprecated.
  - rho
```
@Deprecated
protected double rho
```
    Deprecated.
  - rmsDecay
```
@Deprecated
protected double rmsDecay
```
    Deprecated.
  - adamMeanDecay
```
@Deprecated
protected double adamMeanDecay
```
    Deprecated.
  - adamVarDecay
```
@Deprecated
protected double adamVarDecay
```
    Deprecated.
  - layer
```
protected Layer layer
```
  - leakyreluAlpha
```
@Deprecated
protected double leakyreluAlpha
```
    Deprecated.
  - miniBatch
```
protected boolean miniBatch
```
  - numIterations
```
protected int numIterations
```
  - maxNumLineSearchIterations
```
protected int maxNumLineSearchIterations
```
  - seed
```
protected long seed
```
  - useRegularization
```
protected boolean useRegularization
```
  - optimizationAlgo
```
protected OptimizationAlgorithm optimizationAlgo
```
  - stepFunction
```
protected StepFunction stepFunction
```
  - useDropConnect
```
protected boolean useDropConnect
```
  - minimize
```
protected boolean minimize
```
  - gradientNormalization
```
protected GradientNormalization gradientNormalization
```
  - gradientNormalizationThreshold
```
protected double gradientNormalizationThreshold
```
  - learningRatePolicy
```
protected LearningRatePolicy learningRatePolicy
```
  - lrPolicyDecayRate
```
protected double lrPolicyDecayRate
```
  - lrPolicySteps
```
protected double lrPolicySteps
```
  - lrPolicyPower
```
protected double lrPolicyPower
```
  - pretrain
```
protected boolean pretrain
```
  - trainingWorkspaceMode
```
protected WorkspaceMode trainingWorkspaceMode
```
  - inferenceWorkspaceMode
```
protected WorkspaceMode inferenceWorkspaceMode
```
  - cacheMode
```
protected CacheMode cacheMode
```
  - convolutionMode
```
protected ConvolutionMode convolutionMode
```
- Constructor Detail
  - Builder
```
public Builder()
```
  - Builder
```
public Builder(NeuralNetConfiguration newConf)
```
- Method Detail
  - miniBatch
```
public NeuralNetConfiguration.Builder miniBatch(boolean miniBatch)
```
    Process input as minibatch vs full dataset. Default set to true.
  - trainingWorkspaceMode
```
public NeuralNetConfiguration.Builder trainingWorkspaceMode(@NonNull
                                                            WorkspaceMode workspaceMode)
```
    This method defines Workspace mode being used during training: NONE: workspace won't be used SINGLE: one workspace will be used during whole iteration loop SEPARATE: separate workspaces will be used for feedforward and backprop iteration loops
    
    Parameters:
    
    workspaceMode -
    
    Returns:
  - inferenceWorkspaceMode
```
public NeuralNetConfiguration.Builder inferenceWorkspaceMode(@NonNull
                                                             WorkspaceMode workspaceMode)
```
    This method defines Workspace mode being used during inference: NONE: workspace won't be used SINGLE: one workspace will be used during whole iteration loop SEPARATE: separate workspaces will be used for feedforward and backprop iteration loops
    
    Parameters:
    
    workspaceMode -
    
    Returns:
  - cacheMode
```
public NeuralNetConfiguration.Builder cacheMode(@NonNull
                                                CacheMode cacheMode)
```
    This method defines how/if preOutput cache is handled: NONE: cache disabled (default value) HOST: Host memory will be used DEVICE: GPU memory will be used (on CPU backends effect will be the same as for HOST)
    
    Parameters:
    
    cacheMode -
    
    Returns:
  - useDropConnect
```
public NeuralNetConfiguration.Builder useDropConnect(boolean useDropConnect)
```
    Use drop connect: multiply the weight by a binomial sampling wrt the dropout probability. Dropconnect probability is set using dropOut(double); this is the probability of retaining a weight
    
    Parameters:
    
    useDropConnect - whether to use drop connect or not
    
    Returns:
    
    the
  - minimize
```
public NeuralNetConfiguration.Builder minimize(boolean minimize)
```
    Objective function to minimize or maximize cost function Default set to minimize true.
  - maxNumLineSearchIterations
```
public NeuralNetConfiguration.Builder maxNumLineSearchIterations(int maxNumLineSearchIterations)
```
    Maximum number of line search iterations. Only applies for line search optimizers: Line Search SGD, Conjugate Gradient, LBFGS is NOT applicable for standard SGD
    
    Parameters:
    
    maxNumLineSearchIterations - > 0
    
    Returns:
  - layer
```
public NeuralNetConfiguration.Builder layer(Layer layer)
```
    Layer class.
  - stepFunction
```
public NeuralNetConfiguration.Builder stepFunction(StepFunction stepFunction)
```
    Step function to apply for back track line search. Only applies for line search optimizers: Line Search SGD, Conjugate Gradient, LBFGS Options: DefaultStepFunction (default), NegativeDefaultStepFunction GradientStepFunction (for SGD), NegativeGradientStepFunction
  - list
```
public NeuralNetConfiguration.ListBuilder list()
```
    Create a ListBuilder (for creating a MultiLayerConfiguration)
    Usage:
```
  .list()
 .layer(0,new DenseLayer.Builder()...build())
 ...
 .layer(n,new OutputLayer.Builder()...build())
 
 
```
  - list
```
public NeuralNetConfiguration.ListBuilder list(Layer... layers)
```
    Create a ListBuilder (for creating a MultiLayerConfiguration) with the specified layers
    Usage:
```
  .list(
      new DenseLayer.Builder()...build(),
      ...,
      new OutputLayer.Builder()...build())
 
 
```
    Parameters:
    
    layers - The layer configurations for the network
  - graphBuilder
```
public ComputationGraphConfiguration.GraphBuilder graphBuilder()
```
    Create a GraphBuilder (for creating a ComputationGraphConfiguration).
  - iterations
```
public NeuralNetConfiguration.Builder iterations(int numIterations)
```
    Number of optimization iterations.
  - seed
```
public NeuralNetConfiguration.Builder seed(int seed)
```
    Random number generator seed. Used for reproducability between runs
  - seed
```
public NeuralNetConfiguration.Builder seed(long seed)
```
    Random number generator seed. Used for reproducability between runs
  - optimizationAlgo
```
public NeuralNetConfiguration.Builder optimizationAlgo(OptimizationAlgorithm optimizationAlgo)
```
    Optimization algorithm to use. Most common: OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT
    
    Parameters:
    
    optimizationAlgo - Optimization algorithm to use when training
  - regularization
```
public NeuralNetConfiguration.Builder regularization(boolean useRegularization)
```
    Whether to use regularization (l1, l2, dropout, etc
  - clone
```
public NeuralNetConfiguration.Builder clone()
```
    Overrides:
    
    clone in class Object
  - activation
```
@Deprecated
public NeuralNetConfiguration.Builder activation(String activationFunction)
```
    Deprecated. Use activation(Activation) or @activation(IActivation)
    
    Activation function / neuron non-linearity Typical values include:
    "relu" (rectified linear), "tanh", "sigmoid", "softmax", "hardtanh", "leakyrelu", "maxout", "softsign", "softplus"
  - activation
```
public NeuralNetConfiguration.Builder activation(org.nd4j.linalg.activations.IActivation activationFunction)
```
    Activation function / neuron non-linearity
    
    See Also:
    
    activation(Activation)
  - activation
```
public NeuralNetConfiguration.Builder activation(org.nd4j.linalg.activations.Activation activation)
```
    Activation function / neuron non-linearity
  - leakyreluAlpha
```
@Deprecated
public NeuralNetConfiguration.Builder leakyreluAlpha(double leakyreluAlpha)
```
    Deprecated. Use activation(IActivation) with leaky relu, setting alpha value directly in constructor.
  - weightInit
```
public NeuralNetConfiguration.Builder weightInit(WeightInit weightInit)
```
    Weight initialization scheme.
    
    See Also:
    
    WeightInit
  - biasInit
```
public NeuralNetConfiguration.Builder biasInit(double biasInit)
```
    Constant for bias initialization. Default: 0.0
    
    Parameters:
    
    biasInit - Constant for bias initialization
  - dist
```
public NeuralNetConfiguration.Builder dist(Distribution dist)
```
    Distribution to sample initial weights from. Used in conjunction with .weightInit(WeightInit.DISTRIBUTION).
  - learningRate
```
public NeuralNetConfiguration.Builder learningRate(double learningRate)
```
    Learning rate. Defaults to 1e-1
  - biasLearningRate
```
public NeuralNetConfiguration.Builder biasLearningRate(double biasLearningRate)
```
    Bias learning rate. Set this to apply a different learning rate to the bias
  - learningRateSchedule
```
public NeuralNetConfiguration.Builder learningRateSchedule(Map<Integer,Double> learningRateSchedule)
```
    Learning rate schedule. Map of the iteration to the learning rate to apply at that iteration.
  - learningRateScoreBasedDecayRate
```
public NeuralNetConfiguration.Builder learningRateScoreBasedDecayRate(double lrScoreBasedDecay)
```
    Rate to decrease learningRate by when the score stops improving. Learning rate is multiplied by this rate so ideally keep between 0 and 1.
  - l1
```
public NeuralNetConfiguration.Builder l1(double l1)
```
    L1 regularization coefficient for the weights. Use with .regularization(true)
  - l2
```
public NeuralNetConfiguration.Builder l2(double l2)
```
    L2 regularization coefficient for the weights. Use with .regularization(true)
  - l1Bias
```
public NeuralNetConfiguration.Builder l1Bias(double l1Bias)
```
    L1 regularization coefficient for the bias. Use with .regularization(true)
  - l2Bias
```
public NeuralNetConfiguration.Builder l2Bias(double l2Bias)
```
    L2 regularization coefficient for the bias. Use with .regularization(true)
  - dropOut
```
public NeuralNetConfiguration.Builder dropOut(double dropOut)
```
    Dropout probability. This is the probability of retaining an activation. So dropOut(x) will keep an activation with probability x, and set to 0 with probability 1-x.
    dropOut(0.0) is disabled (default).
    Note: This sets the probability per-layer. Care should be taken when setting lower values for complex networks.
    
    Parameters:
    
    dropOut - Dropout probability (probability of retaining an activation)
  - momentum
```
@Deprecated
public NeuralNetConfiguration.Builder momentum(double momentum)
```
    Deprecated. Use .updater(new Nesterov(momentum)) instead
    
    Momentum rate Used only when Updater is set to Updater.NESTEROVS
  - momentumAfter
```
@Deprecated
public NeuralNetConfiguration.Builder momentumAfter(Map<Integer,Double> momentumAfter)
```
    Deprecated. Use .updater(Nesterov.builder().momentumSchedule(schedule).build()) instead
    
    Momentum schedule. Map of the iteration to the momentum rate to apply at that iteration Used only when Updater is set to Updater.NESTEROVS
  - updater
```
public NeuralNetConfiguration.Builder updater(Updater updater)
```
    Gradient updater. For example, Updater.SGD for standard stochastic gradient descent, Updater.NESTEROV for Nesterov momentum, Updater.RSMPROP for RMSProp, etc.
    Note: default hyperparameters are used with this method. Use updater(IUpdater) to configure the updater-specific hyperparameters.
    
    See Also:
    
    Updater
  - updater
```
public NeuralNetConfiguration.Builder updater(org.nd4j.linalg.learning.config.IUpdater updater)
```
    Gradient updater. For example, Adam or Nesterovs
    
    Parameters:
    
    updater - Updater to use
  - rho
```
@Deprecated
public NeuralNetConfiguration.Builder rho(double rho)
```
    Deprecated. use .updater(new AdaDelta(rho,epsilon)) intead
    
    Ada delta coefficient
    
    Parameters:
    
    rho -
  - epsilon
```
@Deprecated
public NeuralNetConfiguration.Builder epsilon(double epsilon)
```
    Deprecated. Use use .updater(Adam.builder().epsilon(epsilon).build()) or similar instead
    
    Epsilon value for updaters: Adam, RMSProp, Adagrad, Adadelta
    
    Parameters:
    
    epsilon - Epsilon value to use for adagrad or
  - rmsDecay
```
@Deprecated
public NeuralNetConfiguration.Builder rmsDecay(double rmsDecay)
```
    Deprecated. use .updater(new RmsProp(rmsDecay)) intead
    
    Decay rate for RMSProp. Only applies if using .updater(Updater.RMSPROP)
  - adamMeanDecay
```
@Deprecated
public NeuralNetConfiguration.Builder adamMeanDecay(double adamMeanDecay)
```
    Deprecated. use .updater(Adam.builder().beta1(adamMeanDecay).build()) intead
    
    Mean decay rate for Adam updater. Only applies if using .updater(Updater.ADAM)
  - adamVarDecay
```
@Deprecated
public NeuralNetConfiguration.Builder adamVarDecay(double adamVarDecay)
```
    Deprecated. use .updater(Adam.builder().beta2(adamVarDecay).build()) intead
    
    Variance decay rate for Adam updater. Only applies if using .updater(Updater.ADAM)
  - gradientNormalization
```
public NeuralNetConfiguration.Builder gradientNormalization(GradientNormalization gradientNormalization)
```
    Gradient normalization strategy. Used to specify gradient renormalization, gradient clipping etc.
    
    Parameters:
    
    gradientNormalization - Type of normalization to use. Defaults to None.
    
    See Also:
    
    GradientNormalization
  - gradientNormalizationThreshold
```
public NeuralNetConfiguration.Builder gradientNormalizationThreshold(double threshold)
```
    Threshold for gradient normalization, only used for GradientNormalization.ClipL2PerLayer, GradientNormalization.ClipL2PerParamType, and GradientNormalization.ClipElementWiseAbsoluteValue
    Not used otherwise.
    L2 threshold for first two types of clipping, or absolute value threshold for last type of clipping.
  - learningRateDecayPolicy
```
public NeuralNetConfiguration.Builder learningRateDecayPolicy(LearningRatePolicy policy)
```
    Learning rate decay policy. Used to adapt learning rate based on policy.
    
    Parameters:
    
    policy - Type of policy to use. Defaults to None.
  - lrPolicyDecayRate
```
public NeuralNetConfiguration.Builder lrPolicyDecayRate(double lrPolicyDecayRate)
```
    Set the decay rate for the learning rate decay policy.
    
    Parameters:
    
    lrPolicyDecayRate - rate.
  - lrPolicySteps
```
public NeuralNetConfiguration.Builder lrPolicySteps(double lrPolicySteps)
```
    Set the number of steps used for learning decay rate steps policy.
    
    Parameters:
    
    lrPolicySteps - number of steps
  - lrPolicyPower
```
public NeuralNetConfiguration.Builder lrPolicyPower(double lrPolicyPower)
```
    Set the power used for learning rate inverse policy.
    
    Parameters:
    
    lrPolicyPower - power
  - convolutionMode
```
public NeuralNetConfiguration.Builder convolutionMode(ConvolutionMode convolutionMode)
```
  - build
```
public NeuralNetConfiguration build()
```
    Return a configuration based on this builder
    
    Returns:

Class NeuralNetConfiguration.Builder

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

activationFn

weightInit

biasInit

dist

learningRate

biasLearningRate

learningRateSchedule

lrScoreBasedDecay

l1

l2

l1Bias

l2Bias

dropOut

updater

iUpdater

momentum

momentumSchedule

epsilon

rho

rmsDecay

adamMeanDecay

adamVarDecay

layer

leakyreluAlpha

miniBatch

numIterations

maxNumLineSearchIterations

seed

useRegularization

optimizationAlgo

stepFunction

useDropConnect

minimize

gradientNormalization

gradientNormalizationThreshold

learningRatePolicy

lrPolicyDecayRate

lrPolicySteps

lrPolicyPower

pretrain

trainingWorkspaceMode

inferenceWorkspaceMode

cacheMode

convolutionMode

Constructor Detail

Builder

Builder

Method Detail

miniBatch

trainingWorkspaceMode

inferenceWorkspaceMode

cacheMode

useDropConnect

minimize

maxNumLineSearchIterations

layer

stepFunction

list

list

graphBuilder

iterations

seed

seed

optimizationAlgo

regularization

clone

activation

activation

activation

leakyreluAlpha

weightInit

biasInit

dist

learningRate