Constructor and Description |
---|
ParameterLearningOptions() |
Modifier and Type | Method and Description |
---|---|
boolean |
getCalculateStatistics()
Gets a value indicating whether to calculate summary statistics in an extra iteration at the end of learning.
|
Cancellation |
getCancellation()
Gets of sets the instance implementing
Cancellation , used for cancellation. |
ConvergenceMethod |
getConvergenceMethod()
Gets the method used to determine convergence of the learning algorithm.
|
DecisionPostProcessingMethod |
getDecisionPostProcessing()
Gets the post processing method for decision nodes.
|
InitializationOptions |
getInitialization()
Options for initialization.
|
Integer |
getMaximumConcurrency()
Gets the maximum number of inference engines used during learning.
|
int |
getMaximumIterations()
Gets the maximum number of iterations that parameter learning will perform.
|
boolean |
getMonitorLogLikelihood()
Calculates the log likelihood at each iteration.
|
Priors |
getPriors()
Contains parameters used to avoid boundary conditions during learning.
|
ParameterLearningProgress |
getProgress()
Gets of sets the instance implementing
ParameterLearningProgress , used for progress notifications. |
boolean |
getSaveHyperparameters()
Gets a value indicating whether hyperparameters (e.g.
|
Integer |
getSeed()
Gets the seed used to generate random numbers for initialization.
|
Stop |
getStopping()
Gets the instance implementing
Stop used for early stopping. |
TimeSeriesMode |
getTimeSeriesMode()
Gets the mode in which time series distributions are learned.
|
Double |
getTolerance()
Gets the tolerance used to determine whether or not parameter learning has converged.
|
double |
getToleranceOrDefault()
If Tolerance is null, this returns the default tolerance for the given convergence method, otherwise Tolerance is returned.
|
void |
setCalculateStatistics(boolean value)
Sets a value indicating whether to calculate summary statistics in an extra iteration at the end of learning.
|
void |
setCancellation(Cancellation value)
Gets of sets the instance implementing
Cancellation , used for cancellation. |
void |
setConvergenceMethod(ConvergenceMethod value)
Sets the method used to determine convergence of the learning algorithm.
|
void |
setDecisionPostProcessing(DecisionPostProcessingMethod value)
Sets the post processing method for decision nodes.
|
void |
setMaximumConcurrency(Integer value)
Sets the maximum number of inference engines used during learning.
|
void |
setMaximumIterations(int value)
Sets the maximum number of iterations that parameter learning will perform.
|
void |
setMonitorLogLikelihood(boolean value)
Calculates the log likelihood at each iteration.
|
void |
setProgress(ParameterLearningProgress value)
Gets of sets the instance implementing
ParameterLearningProgress , used for progress notifications. |
void |
setSaveHyperparameters(boolean value)
Sets a value indicating whether hyperparameters (e.g.
|
void |
setSeed(Integer value)
Sets the seed used to generate random numbers for initialization.
|
void |
setStopping(Stop value)
Sets the instance implementing
Stop used for early stopping. |
void |
setTimeSeriesMode(TimeSeriesMode value)
Sets the mode in which time series distributions are learned.
|
void |
setTolerance(Double value)
Sets the tolerance used to determine whether or not parameter learning has converged.
|
public Integer getMaximumConcurrency()
During learning, multiple inference engines may be used in parallel. However each inference engine has its own memory requirements for inference, and so this parameter allows the number to be limited, to avoid excessive memory consumption. The amount of memory used per inference engine, depends on the Network
and also the data.
public void setMaximumConcurrency(Integer value)
During learning, multiple inference engines may be used in parallel. However each inference engine has its own memory requirements for inference, and so this parameter allows the number to be limited, to avoid excessive memory consumption. The amount of memory used per inference engine, depends on the Network
and also the data.
public ConvergenceMethod getConvergenceMethod()
public void setConvergenceMethod(ConvergenceMethod value)
public boolean getCalculateStatistics()
true
statistics are calculated.public void setCalculateStatistics(boolean value)
value
- When true
statistics are calculated.public boolean getSaveHyperparameters()
public void setSaveHyperparameters(boolean value)
public boolean getMonitorLogLikelihood()
False
by default, as it can be expensive to calculate.
This property does not effect the output of statistics on completion of learning.public void setMonitorLogLikelihood(boolean value)
False
by default, as it can be expensive to calculate.
This property does not effect the output of statistics on completion of learning.public Priors getPriors()
public Integer getSeed()
getMaximumConcurrency()
is 1 and when not distributed.public void setSeed(Integer value)
getMaximumConcurrency()
is 1 and when not distributed.public InitializationOptions getInitialization()
DistributionSpecification
can override certain initialization values.public DecisionPostProcessingMethod getDecisionPostProcessing()
public void setDecisionPostProcessing(DecisionPostProcessingMethod value)
public TimeSeriesMode getTimeSeriesMode()
public void setTimeSeriesMode(TimeSeriesMode value)
public int getMaximumIterations()
getTolerance()
.public void setMaximumIterations(int value)
getTolerance()
.value
- Maximum iterations.public Stop getStopping()
Stop
used for early stopping.
Stopping is different to cancellation, as stopping will still complete the learning process, albeit having performed fewer iterations.public void setStopping(Stop value)
Stop
used for early stopping.
Stopping is different to cancellation, as stopping will still complete the learning process, albeit having performed fewer iterations.value
- The instance used for stopping.public Cancellation getCancellation()
Cancellation
, used for cancellation.Cancellation
public void setCancellation(Cancellation value)
Cancellation
, used for cancellation.Cancellation
public ParameterLearningProgress getProgress()
ParameterLearningProgress
, used for progress notifications.ParameterLearningProgress
public void setProgress(ParameterLearningProgress value)
ParameterLearningProgress
, used for progress notifications.ParameterLearningProgress
public double getToleranceOrDefault()
public Double getTolerance()
When null, a default value is used which depends on the Convergence Method in use.
public void setTolerance(Double value)
When null, a default value is used which depends on the Convergence Method in use.
value
- The tolerance.Copyright © 2023. All rights reserved.