Config:ModelBuilder
From SUMOwiki
Jump to navigationJump to searchAdaptiveModelBuilder
rational
Build rational models
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SequentialModelBuilder|SequentialModelBuilder]]" combineOutputs="false"><!-- Maximum number of models built before selecting new samples -->
<Option key="maximumRunLength" value="30"/><!-- Degeneration of score if a model gets older -->
<Option key="decay" value=".99"/><!-- Size of the best model history -->
<Option key="historySize" value="15"/><!-- One of best, last. When set to best the best `historySize' models are kept,
- - when set to last, the last `historySize' models are kept -->
<Option key="strategy" value="best"/><!-- <Option key="strategy" value="window"/> -->
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RationalSequentialInterface|RationalSequentialInterface]]"><!-- Bounds for the weights of the rational modeller -->
<Option key="weightBounds" value="1,40"/><!-- Bounds for the percentage of degrees of freedom wrt number of samples -->
<Option key="percentBounds" value="1,100"/><!-- Regardless of the percentage bounds, never use more than this many degrees of freedom -->
<Option key="maxDegrees" value="100"/><!-- When randomizing rational flags, what percentage should be set -->
<Option key="percentRational" value="70"/><!-- If a variable is named "f" of "frequency" it will be modelled differently, if this is set to auto,
- - If this field is set to a variable name, that variable will be considered to be the frequency -->
<Option key="frequencyVariable" value="auto"/><!-- Base function for interpolation, one of chebyshev, power, legendre -->
<Option key="basis" value="chebyshev"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
rationalgenetic
Build rational models using a genetic algorithm
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!--See that matlab gads toolbox documentation for more information on the options-->
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="15"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RationalGeneticInterface|RationalGeneticInterface]]">
<Option key="crossoverFcn" value="crossover"/>
<Option key="mutationFcn" value="mutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="creationFcn" value="initial"/><!-- Bounds for the weights of the rational modeller -->
<Option key="weightBounds" value="1,40"/><!-- Bounds for the percentage of degrees of freedom wrt number of samples -->
<Option key="percentBounds" value="1,100"/><!-- Regardless of the percentage bounds, never use more than this many degrees of freedom -->
<Option key="maxDegrees" value="100"/><!-- When randomizing rational flags, what percentage should be set -->
<Option key="percentRational" value="70"/><!-- If a variable is named "f" of "frequency"
it will be modelled differently, if this is set to auto --><!-- If this field is set to a variable name, that variable will be considered to be the frequency -->
<Option key="frequencyVariable" value="auto"/><!-- Base function for interpolation, one of chebyshev, power, legendre -->
<Option key="basis" value="chebyshev"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
RBF
Build Radial Basis Function models
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SequentialModelBuilder|SequentialModelBuilder]]" combineOutputs="false"><!-- Maximum number of models built before selecting new samples -->
<Option key="maximumRunLength" value="20"/><!-- Degeneration of score if a model gets older -->
<Option key="decay" value=".9"/><!-- Size of the best model history -->
<Option key="historySize" value="15"/><!-- One of best, last. When set to best the best `historySize' models are kept,
- - when set to last, the last `historySize' models are kept -->
<Option key="strategy" value="best"/><!-- <Option key="strategy" value="window"/> -->
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#BFSequentialInterface|BFSequentialInterface]]">
<Option key="type" value="RBF"/>
<[[Config:BasisFunction|BasisFunction]] name="gaussian" min=".1" max="5" scale="log"/>
<[[Config:BasisFunction|BasisFunction]] name="multiquadric" min=".1" max="5" scale="log"/><!--<[[Config:BasisFunction|BasisFunction]] name="biharmonic" min=".1" max="5" scale="log"/> -->
<[[Config:BasisFunction|BasisFunction]] name="exponential" min=".1,.5" max="5,2" scale="log,lin"/>
<Option key="regression" value="-1,0,1,2"/>
<Option key="backend" value="AP"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
RBFgenetic
Build Radial Basis Function models using a genetic algorithm
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!--See that matlab gads toolbox documentation for more information on the options-->
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="15"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#BFGeneticInterface|BFGeneticInterface]]">
<Option key="type" value="RBF"/>
<Option key="crossoverFcn" value="crossover"/>
<Option key="mutationFcn" value="mutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="creationFcn" value="initial"/><!-- Bounds for the shape parameter -->
<[[Config:BasisFunction|BasisFunction]] name="gaussian" min=".1" max="5" scale="log"/>
<[[Config:BasisFunction|BasisFunction]] name="multiquadric" min=".1" max="5" scale="log"/><!-- <[[Config:BasisFunction|BasisFunction]] name="biharmonic" min=".1" max="5" scale="log"/> -->
<[[Config:BasisFunction|BasisFunction]] name="exponential" min=".1,.5" max="5,2" scale="log,lin"/>
<Option key="regression" value="-1,0,1,2"/><!-- Basisfunction, one of 'multiquadric', 'triharmonic', 'biharmonic' --><!-- Specify which implementation to use, currently, 'Direct', 'AP', 'Greedy' and
'FastRBF' are supported.
'Direct' solves the direct problem by inverting the interpolation
matrix
'AP' uses an alternating projections method when the system gets
too large. This is *MUCH* slower than 'Direct', and doesn't
guarantee convergence, use with caution
'Greedy' uses a one point greedy algorithm for selecting the
interpolation centers. Same remark applies as with 'AP'
'FastRBF' interfaces the FastRBF library. When using FastRBF,
make sure your copy of the software is installed under
the src/matlab/contrib directory and that the software
is licensed properly.
The FastRBF matlab toolbox can be found at
http://www.farfieldtechnology.com
-->
<Option key="backend" value="AP"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
DACE
Build DACE models (= functionally equivalent to Kriging, but a custom implementation)
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SequentialModelBuilder|SequentialModelBuilder]]" combineOutputs="false"><!-- Maximum number of models built before selecting new samples -->
<Option key="maximumRunLength" value="20"/><!-- Degeneration of score if a model gets older -->
<Option key="decay" value=".9"/><!-- Size of the best model history -->
<Option key="historySize" value="15"/><!-- One of best, last. When set to best the best `historySize' models are kept,
- - when set to last, the last `historySize' models are kept -->
<Option key="strategy" value="best"/><!-- <Option key="strategy" value="window"/> -->
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#BFSequentialInterface|BFSequentialInterface]]">
<Option key="type" value="DACE"/>
<[[Config:BasisFunction|BasisFunction]] name="gaussian" min=".1" max="5" scale="log"/>
<[[Config:BasisFunction|BasisFunction]] name="multiquadric" min=".1" max="5" scale="log"/><!--<[[Config:BasisFunction|BasisFunction]] name="biharmonic" min=".1" max="5" scale="log"/> -->
<[[Config:BasisFunction|BasisFunction]] name="exponential" min=".1,.5" max="5,2" scale="log,lin"/>
<Option key="regression" value="-1,0,1,2"/>
<Option key="backend" value="AP"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
DACEgenetic
Build DACE models (= functionally equivalent to Kriging, but a custom implementation)
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!--See that matlab gads toolbox documentation for more information on the options-->
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="15"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#BFGeneticInterface|BFGeneticInterface]]">
<Option key="type" value="DACE"/>
<Option key="crossoverFcn" value="crossover"/>
<Option key="mutationFcn" value="mutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="creationFcn" value="initial"/><!-- Bounds for the shape parameter -->
<[[Config:BasisFunction|BasisFunction]] name="gaussian" min=".1" max="5" scale="log"/>
<[[Config:BasisFunction|BasisFunction]] name="multiquadric" min=".1" max="5" scale="log"/><!-- <[[Config:BasisFunction|BasisFunction]] name="biharmonic" min=".1" max="5" scale="log"/> -->
<[[Config:BasisFunction|BasisFunction]] name="exponential" min=".1,.5" max="5,2" scale="log,lin"/>
<Option key="regression" value="-1,0,1,2"/>
<Option key="backend" value="AP"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
DACEps
Build DACE models (= functionally equivalent to Kriging, but a custom implementation)
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PatternSearchModelBuilder|PatternSearchModelBuilder]]" combineOutputs="false"><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<Option key="searchMethod" value="GPSPositiveBasis2N"/>
<Option key="pollMethod" value="MADSPositiveBasis2N"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#BFOptimizationInterface|BFOptimizationInterface]]">
<Option key="type" value="DACE"/><!--Option key="multipleBasisFunctionsAllowed" value="false"/-->
<[[Config:BasisFunction|BasisFunction]] name="gaussian" min=".1" max="5" scale="log"/>
<Option key="regression" value="-1,0,1,2"/>
<Option key="backend" value="AP"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
DACEpso
Build DACE models (= functionally equivalent to Kriging, but a custom implementation)
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PatternSearchModelBuilder|PatternSearchModelBuilder]]" combineOutputs="false"><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="true"/><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<[[Config:Optimizer|Optimizer]] type="[[Optimizer#PSOtOptimizer|PSOtOptimizer]]">
<Option key="typePSO" value="0"/>
<Option key="seedPSO" value="1"/>
<Option key="popSize" value="10"/>
<Option key="maxiters" value="10"/>
<Option key="epochInertia" value="8"/>
<Option key="gradientTermination" value="8"/>
</[[Config:Optimizer|Optimizer]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#BFOptimizationInterface|BFOptimizationInterface]]">
<Option key="type" value="DACE"/><!--Option key="multipleBasisFunctionsAllowed" value="false"/-->
<[[Config:BasisFunction|BasisFunction]] name="gaussian" min=".1" max="5" scale="log"/>
<Option key="regression" value="-1,0,1,2"/>
<Option key="backend" value="AP"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
krigingsim
Build kriging models using Simulated Annealing (requires matlab v7.4)
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SimAnnealingModelBuilder|SimAnnealingModelBuilder]]" combineOutputs="false"><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#KrigingInterface|KrigingInterface]]">
<Option key="lowerThetaBound" value="-5"/>
<Option key="upperThetaBound" value="3"/>
<Option key="regressionFunction" value="regpoly0"/>
<Option key="correlationFunction" value="corrgauss"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
krigingps
Build kriging models using pattern search
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PatternSearchModelBuilder|PatternSearchModelBuilder]]" combineOutputs="false"><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<Option key="searchMethod" value="GPSPositiveBasis2N"/>
<Option key="pollMethod" value="MADSPositiveBasis2N"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#KrigingInterface|KrigingInterface]]">
<Option key="lowerThetaBound" value="-5"/>
<Option key="upperThetaBound" value="3"/>
<Option key="regressionFunction" value="regpoly0"/>
<Option key="correlationFunction" value="corrgauss"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
krigingoptim
Build kriging models using the matlab optimization toolbox
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#OptimToolboxModelBuilder|OptimToolboxModelBuilder]]" combineOutputs="false"><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#KrigingInterface|KrigingInterface]]">
<Option key="lowerThetaBound" value="-5"/>
<Option key="upperThetaBound" value="3"/>
<Option key="regressionFunction" value="regpoly0"/>
<Option key="correlationFunction" value="corrgauss"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
kriginggenetic
Build kriging models using a genetic algorithm
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="populationType" value="doubleVector"/>
<Option key="populationSize" value="10"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#KrigingGeneticInterface|KrigingGeneticInterface]]">
<Option key="creationFcn" value="@gacreationuniform"/>
<Option key="crossoverFcn" value="@crossoversinglepoint"/>
<Option key="mutationFcn" value="@mutationgaussian"/>
<Option key="constraintFcn" value="[]"/>
<Option key="lowerThetaBound" value="-5"/>
<Option key="upperThetaBound" value="3"/>
<Option key="regressionFunction" value="regpoly0"/>
<Option key="correlationFunction" value="corrgauss"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
krigingpso
Build kriging models using PSO
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PSOModelBuilder|PSOModelBuilder]]" combineOutputs="false"><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<[[Config:Optimizer|Optimizer]] type="[[Optimizer#PSOtOptimizer|PSOtOptimizer]]">
<Option key="typePSO" value="0"/>
<Option key="seedPSO" value="1"/>
<Option key="popSize" value="10"/>
<Option key="maxiters" value="10"/>
<Option key="epochInertia" value="8"/>
<Option key="gradientTermination" value="8"/>
</[[Config:Optimizer|Optimizer]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#KrigingInterface|KrigingInterface]]">
<Option key="lowerThetaBound" value="-5"/>
<Option key="upperThetaBound" value="3"/>
<Option key="regressionFunction" value="regpoly0"/>
<Option key="correlationFunction" value="corrgauss"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
krigingrandom
Build kriging models randomly
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#RandomModelBuilder|RandomModelBuilder]]" combineOutputs="false"><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="runSize" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#KrigingInterface|KrigingInterface]]">
<Option key="lowerThetaBound" value="-5"/>
<Option key="upperThetaBound" value="3"/>
<Option key="regressionFunction" value="regpoly0"/>
<Option key="correlationFunction" value="corrgauss"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
splines
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SequentialModelBuilder|SequentialModelBuilder]]" combineOutputs="false">
<Option key="maximumRunLength" value="30"/>
<Option key="decay" value=".99"/>
<Option key="historySize" value="15"/>
<Option key="strategy" value="best"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SplineSequentialInterface|SplineSequentialInterface]]">
<Option key="smoothingBounds" value="0,1"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
splinesgenetic
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="10"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SplineGeneticInterface|SplineGeneticInterface]]">
<Option key="creationFcn" value="createInitialPopulation"/>
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="smoothingBounds" value="0,1"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
splinessim
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SimAnnealingModelBuilder|SimAnnealingModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SplineInterface|SplineInterface]]">
<Option key="smoothingBounds" value="0,1"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
splinesps
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PatternSearchModelBuilder|PatternSearchModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<Option key="searchMethod" value="GPSPositiveBasis2N"/>
<Option key="pollMethod" value="MADSPositiveBasis2N"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SplineInterface|SplineInterface]]">
<Option key="smoothingBounds" value="0,1"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
splinesoptim
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#OptimToolboxModelBuilder|OptimToolboxModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SplineInterface|SplineInterface]]">
<Option key="smoothingBounds" value="0,1"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
annbatch
Maintain a population (batch) of feedforward neural networks and mutation to search the parameter space See the matlab neural network toolbox for more information
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#BatchModelBuilder|BatchModelBuilder]]" combineOutputs="false">
<Option key="batchSize" value="10"/><!--One adaptive modeling iteration stops after one of the following two thresholds have been reached-->
<Option key="maxBatches" value="10"/>
<Option key="maxBatchesNoImprovement" value="4"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#ANNBatchInterface|ANNBatchInterface]]"><!--initial hidden layer dimension-->
<Option key="initialSize" value="3,3"/><!--comma separated list of allowed learning rules-->
<Option key="allowedLearningRules" value="trainbr"/><!--performance function to use, empty uses training rule default default-->
<Option key="performFcn" value=""/><!--how many epochs to train for-->
<Option key="epochs" value="300"/><!--max time to train for-->
<Option key="trainingTime" value="Inf"/><!--range of initial random weights-->
<Option key="initWeightRange" value="-0.8,0.8"/><!--mutation changes x neurons at a time (in a random layer) with x in [lb ub]-->
<Option key="hiddenUnitDelta" value="-2,3"/><!--train until the error reaches this goal-->
<Option key="trainingGoal" value="0"/><!--show training progress every x epochs, set to NaN to disable-->
<Option key="trainingProgress" value="NaN"/><!--How to train the network, one of 'auto', 'earlyStopping', 'crossvalidation'
auto: train with early stopping unless regularization is employed
Set to any other value for simply training on all the data, doing nothing special -->
<Option key="trainMethod" value="auto"/><!--the training set - validation set - testset ratios-->
<Option key="earlyStoppingRatios" value="0.80,0.20,0"/><!-- Transfer function to use for all hidden layers and the output layer
So should be a list of max 2 items -->
<Option key="transferFunctionTemplate" value="tansig,purelin"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
anngenetic
Use the matlab gads toolbox to select ANN parameters using a GA
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!--See that matlab gads toolbox documentation for more information on the options-->
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="10"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#ANNGeneticInterface|ANNGeneticInterface]]">
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="creationFcn" value="createInitialPopulation"/><!--initial hidden layer dimension-->
<Option key="initialSize" value="3,3"/><!--comma separated list of allowed learning rules-->
<Option key="allowedLearningRules" value="trainbr,trainlm,trainscg"/><!--performance function to use, empty uses training rule default default-->
<Option key="performFcn" value=""/><!--how many epochs to train for-->
<Option key="epochs" value="300"/><!--max time to train for-->
<Option key="trainingTime" value="Inf"/><!--range of initial random weights-->
<Option key="initWeightRange" value="-0.8,0.8"/><!--mutation changes x neurons at a time (in a random layer) with x in [lb ub]-->
<Option key="hiddenUnitDelta" value="-2,3"/><!--train until the error reaches this goal-->
<Option key="trainingGoal" value="0"/><!--show training progress every x epochs, set to NaN to disable-->
<Option key="trainingProgress" value="NaN"/><!--How to train the network, one of 'auto', 'earlyStopping', 'crossvalidation'
auto: train with early stopping unless regularization is employed
Set to any other value for simply training on all the data, doing nothing special -->
<Option key="trainMethod" value="auto"/><!--the training set - validation set - testset ratios-->
<Option key="earlyStoppingRatios" value="0.80,0.20,0"/><!-- Transfer function to use for all hidden layers and the output layer
So should be a list of max 2 items -->
<Option key="transferFunctionTemplate" value="tansig,purelin"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
annrandom
Random ANN model builder, usefull as a baseline comparison
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#RandomModelBuilder|RandomModelBuilder]]" combineOutputs="false"><!--This many iterations before allowing new samples-->
<Option key="runSize" value="10"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#ANNInterface|ANNInterface]]">
<Option key="allowedLearningRules" value="trainbr,trainlm,trainscg"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
fanngenetic
Use the matlab gads toolbox to select ANN parameters using a GA (based on the FANN library)
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!--See that matlab gads toolbox documentation for more information on the options-->
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="10"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#FANNGeneticInterface|FANNGeneticInterface]]">
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="creationFcn" value="createInitialPopulation"/><!--initial hidden layer dimension-->
<Option key="initialSize" value="4,4"/><!--how many epochs to train for-->
<Option key="epochs" value="1500"/><!--range of initial random weights-->
<Option key="initWeightRange" value="-0.8,0.8"/><!--mutation changes x neurons at a time (in a random layer) with x in [lb ub]-->
<Option key="hiddenUnitDelta" value="-2,2"/><!--train until the error reaches this goal-->
<Option key="trainingGoal" value="0"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
nanngenetic
Use the matlab gads toolbox to select ANN parameters using a GA (based on the NNSYSID library)
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!--See that matlab gads toolbox documentation for more information on the options-->
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="10"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#NANNGeneticInterface|NANNGeneticInterface]]">
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="creationFcn" value="createInitialPopulation"/><!--initial hidden layer dimension-->
<Option key="initialSize" value="10"/><!--how many epochs to train for-->
<Option key="epochs" value="500"/><!--range of initial random weights-->
<Option key="initWeightRange" value="-0.8,0.8"/><!--mutation changes x neurons at a time (in a random layer) with x in [lb ub]-->
<Option key="hiddenUnitDelta" value="-2,3"/><!-- pruning techniques used : 0: none, 1: Mag Threshold, 2: Iterative Mag, 3: OBD, 4: OBS -->
<Option key="allowedPruneTechniques" value="0,1,2,3,4"/><!-- threshold for magnitude based pruning -->
<Option key="threshold" value="0.2"/><!-- retrain epochs while pruning-->
<Option key="retrain" value="50"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
lssvmgenetic
Use the matlab gads toolbox to select LSSVM parameters using a GA
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!--See the matlab gads toolbox documentation for more information on the options--><!--<Option key="populationType" value="doubleVector"/>-->
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="10"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMGeneticInterface|SVMGeneticInterface]]"><!--<Option key="creationFcn" value="@gacreationuniform"/>
<Option key="crossoverFcn" value="@crossoversinglepoint"/>
<Option key="mutationFcn" value="@mutationgaussian"/>-->
<Option key="creationFcn" value="createInitialPopulation"/>
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="backend" value="lssvm"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
lssvmps
Use the matlab gads toolbox to select LSSVM parameters using Pattern Search
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PatternSearchModelBuilder|PatternSearchModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!--See that matlab gads toolbox documentation for more information on the options-->
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<Option key="searchMethod" value="GPSPositiveBasis2N"/>
<Option key="pollMethod" value="MADSPositiveBasis2N"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="lssvm"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
lssvmoptim
Use the matlab optimization toolbox to select LSSVM parameters
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#OptimToolboxModelBuilder|OptimToolboxModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!--See the interface matlab file and the optimization toolbox documentation for more information on the options-->
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="lssvm"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
lssvmpso
Use the PSO toolbox to select LSSVM parameters using Particle Swarm Optimization
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PSOModelBuilder|PSOModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/>
<[[Config:Optimizer|Optimizer]] type="[[Optimizer#PSOtOptimizer|PSOtOptimizer]]">
<Option key="typePSO" value="0"/>
<Option key="seedPSO" value="1"/>
<Option key="popSize" value="10"/>
<Option key="maxiters" value="10"/>
<Option key="epochInertia" value="8"/>
<Option key="gradientTermination" value="8"/>
</[[Config:Optimizer|Optimizer]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="lssvm"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
lssvmsim
Use the matlab gads toolbox to select LSSVM parameters using simulated annealing
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SimAnnealingModelBuilder|SimAnnealingModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!--See the interface matlab file and the gads toolbox documentation for more information on the options-->
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="lssvm"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
lssvmdirect
Use the DIviding RECtangles algorithm to optimize the LS-SVM hyperparameters
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#OptimizerModelBuilder|OptimizerModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/>
<[[Config:Optimizer|Optimizer]] type="[[Optimizer#DirectOptimizer|DirectOptimizer]]">
<Option key="maxits" value="500"/>
<Option key="maxevals" value="100"/>
</[[Config:Optimizer|Optimizer]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="lssvm"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
lssvmrandom
Generate random LSSVM models
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#RandomModelBuilder|RandomModelBuilder]]" combineOutputs="false">
<Option key="runSize" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="lssvm"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
svmgenetic
Use the matlab gads toolbox to select SVM parameters using a GA
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!--See the interface matlab file and the gads toolbox documentation for more information on the options-->
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="10"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMGeneticInterface|SVMGeneticInterface]]"><!--<Option key="creationFcn" value="@gacreationuniform"/>
<Option key="crossoverFcn" value="@crossoversinglepoint"/>
<Option key="mutationFcn" value="@mutationgaussian"/>-->
<Option key="creationFcn" value="createInitialPopulation"/>
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="backend" value="libSVM"/>
<Option key="type" value="epsilon-SVR"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
<Option key="nu" value="0.01"/>
<Option key="epsilon" value="0"/>
<Option key="stoppingTolerance" value="1e-6"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
svmps
Use the matlab gads toolbox to select SVM parameters using Pattern Search
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PatternSearchModelBuilder|PatternSearchModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!--See the interface matlab file and the gads toolbox documentation for more information on the options-->
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<Option key="searchMethod" value="GPSPositiveBasis2N"/>
<Option key="pollMethod" value="MADSPositiveBasis2N"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="libSVM"/>
<Option key="type" value="epsilon-SVR"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
<Option key="nu" value="0.01"/>
<Option key="epsilon" value="0"/>
<Option key="stoppingTolerance" value="1e-6"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
svmsim
Use the matlab gads toolbox to select SVM parameters using simulated annealing
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SimAnnealingModelBuilder|SimAnnealingModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!--See the interface matlab file and the gads toolbox documentation for more information on the options-->
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="libSVM"/>
<Option key="type" value="epsilon-SVR"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
<Option key="nu" value="0.01"/>
<Option key="epsilon" value="0"/>
<Option key="stoppingTolerance" value="1e-6"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
svmoptim
Use the matlab optimization toolbox to select SVM parameters
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#OptimToolboxModelBuilder|OptimToolboxModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/><!--See the interface matlab file and the optimization toolbox documentation for more
information on the options-->
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="libSVM"/>
<Option key="type" value="epsilon-SVR"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
<Option key="nu" value="0.01"/>
<Option key="epsilon" value="0"/>
<Option key="stoppingTolerance" value="1e-6"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
svmpso
Use the PSO toolbox to select SVM parameters using Particle Swarm Optimization
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PSOModelBuilder|PSOModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/>
<[[Config:Optimizer|Optimizer]] type="[[Optimizer#PSOtOptimizer|PSOtOptimizer]]">
<Option key="typePSO" value="0"/>
<Option key="seedPSO" value="1"/>
<Option key="popSize" value="10"/>
<Option key="maxiters" value="10"/>
<Option key="epochInertia" value="8"/>
<Option key="gradientTermination" value="8"/>
</[[Config:Optimizer|Optimizer]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="libSVM"/>
<Option key="type" value="epsilon-SVR"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
<Option key="nu" value="0.01"/>
<Option key="epsilon" value="0"/>
<Option key="stoppingTolerance" value="1e-6"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
svmdirect
Use the DIviding RECtangles algorithm to optimize the SVM hyperparameters
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#OptimizerModelBuilder|OptimizerModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/><!-- Plot the optimization surface, visualizes the search through the parameter space (2D only) -->
<Option key="plotOptimSurface" value="false"/>
<[[Config:Optimizer|Optimizer]] type="[[Optimizer#DirectOptimizer|DirectOptimizer]]">
<Option key="maxits" value="500"/>
<Option key="maxevals" value="100"/>
</[[Config:Optimizer|Optimizer]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="libSVM"/>
<Option key="type" value="epsilon-SVR"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
<Option key="nu" value="0.01"/>
<Option key="epsilon" value="0"/>
<Option key="stoppingTolerance" value="1e-6"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
svmrandom
Generate random SVMs
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#RandomModelBuilder|RandomModelBuilder]]" combineOutputs="false">
<Option key="runSize" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMInterface|SVMInterface]]">
<Option key="backend" value="libSVM"/>
<Option key="type" value="epsilon-SVR"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
<Option key="nu" value="0.01"/>
<Option key="epsilon" value="0"/>
<Option key="stoppingTolerance" value="1e-6"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
rbfnnbatch
Batch model builder for Radial Basis Function Neural networks See the matlab neural network toolbox for more information
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#BatchModelBuilder|BatchModelBuilder]]" combineOutputs="false">
<Option key="maxBatches" value="10"/>
<Option key="maxBatchesNoImprovement" value="3"/>
<Option key="batchSize" value="10"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RBFNNBatchInterface|RBFNNBatchInterface]]"><!--Error goal when constructing the network-->
<Option key="goal" value="0"/><!--Initial value for the spread -->
<Option key="spread" value="1"/><!--Spread bounds -->
<Option key="spreadBounds" value="0.0001,2"/><!--Maximum number of neurons to use per network-->
<Option key="maxNeurons" value="100"/>
<Option key="trainingProgress" value="Inf"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
rbfnngenetic
Genetic model builder for Radial Basis Function Neural networks See the matlab neural network toolbox for more information
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="populationType" value="custom"/>
<Option key="populationSize" value="10"/>
<Option key="maxGenerations" value="10"/>
<Option key="eliteCount" value="1"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RBFNNGeneticInterface|RBFNNGeneticInterface]]">
<Option key="creationFcn" value="createInitialPopulation"/>
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/>
<Option key="constraintFcn" value="[]"/><!--Error goal when constructing the network-->
<Option key="goal" value="0"/><!--Initial value for the spread -->
<Option key="spread" value="1"/><!--Spread bounds -->
<Option key="spreadBounds" value="0.0001,2"/><!--Maximum number of neurons to use per network-->
<Option key="maxNeurons" value="100"/>
<Option key="trainingProgress" value="Inf"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
rbfnnoptim
Build Radial Basis Function Neural networks using the Matlab Optimization Toolbox
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#OptimToolboxModelBuilder|OptimToolboxModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="300"/>
<Option key="maxFunEvals" value="300"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RBFNNInterface|RBFNNInterface]]"><!--Error goal when constructing the network-->
<Option key="goal" value="0"/><!--Initial value for the spread -->
<Option key="spread" value="1"/><!--Spread bounds -->
<Option key="spreadBounds" value="0.0001,3"/><!--Maximum number of neurons to use per network-->
<Option key="maxNeurons" value="100"/>
<Option key="trainingProgress" value="Inf"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
rbfnnps
Build Radial Basis Function Neural networks using Pattern Search
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#PatternSearchModelBuilder|PatternSearchModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<Option key="searchMethod" value="GPSPositiveBasis2N"/>
<Option key="pollMethod" value="MADSPositiveBasis2N"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RBFNNInterface|RBFNNInterface]]"><!--Error goal when constructing the network-->
<Option key="goal" value="0"/><!--Initial value for the spread -->
<Option key="spread" value="1"/><!--Spread bounds -->
<Option key="spreadBounds" value="0.0001,3"/><!--Maximum number of neurons to use per network-->
<Option key="maxNeurons" value="100"/>
<Option key="trainingProgress" value="Inf"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
rbfnnsim
Build Radial Basis Function Neural networks using Pattern Search
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#SimAnnealingModelBuilder|SimAnnealingModelBuilder]]" combineOutputs="false"><!-- Re-start strategy for resuming the optimization process between sampling iterations.
One of 'random','continue','model' and 'intelligent' (Default). See the docs for more information -->
<Option key="restartStrategy" value="intelligent"/>
<Option key="maxIterations" value="500"/>
<Option key="maxFunEvals" value="100"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RBFNNInterface|RBFNNInterface]]"><!--Error goal when constructing the network-->
<Option key="goal" value="0"/><!--Initial value for the spread -->
<Option key="spread" value="1"/><!--Spread bounds -->
<Option key="spreadBounds" value="0.0001,3"/><!--Maximum number of neurons to use per network-->
<Option key="maxNeurons" value="100"/>
<Option key="trainingProgress" value="Inf"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
rbfnnrandom
Build random RBF neural networks
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#RandomModelBuilder|RandomModelBuilder]]" combineOutputs="false">
<Option key="runSize" value="10"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RBFNNInterface|RBFNNInterface]]"><!--Error goal when constructing the network-->
<Option key="goal" value="0"/><!--Initial value for the spread -->
<Option key="spread" value="1"/><!--Spread bounds -->
<Option key="spreadBounds" value="0.0001,3"/><!--Maximum number of neurons to use per network-->
<Option key="maxNeurons" value="100"/>
<Option key="trainingProgress" value="Inf"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
heterogenetic
A heterogeneous genetic model builder. Uses a genetic algorithm with speciation (island model) to evolve different model types together. The models types compete against each other until the best model prevails.
<[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]] type="[[AdaptiveModelBuilder#GeneticModelBuilder|GeneticModelBuilder]]" combineOutputs="false">
<Option key="populationType" value="custom"/><!-- the population size must match the number of model interfaces minus 1 -->
<Option key="populationSize" value="10,10,10"/>
<Option key="maxGenerations" value="10"/>
<Option key="crossoverFraction" value="0.7"/>
<Option key="eliteCount" value="1"/>
<Option key="stallGenLimit" value="4"/>
<Option key="stallTimeLimit" value="Inf"/>
<Option key="migrationDirection" value="forward"/>
<Option key="migrationFraction" value="0.1"/>
<Option key="migrationInterval" value="3"/><!-- Do we want to prevent any model type going completely extinct -->
<Option key="extinctionPrevention" value="no"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#HeterogeneousGeneticInterface|HeterogeneousGeneticInterface]]">
<Option key="creationFcn" value="createInitialPopulation"/>
<Option key="crossoverFcn" value="crossover"/>
<Option key="mutationFcn" value="mutate"/>
<Option key="constraintFcn" value="[]"/>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#EnsembleGeneticInterface|EnsembleGeneticInterface]]">
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/><!-- the maximum ensemble size -->
<Option key="maxSize" value="4"/><!-- Ensemble members should differ this much percent -->
<Option key="equalityThreshold" value="0.05"/>
</[[Config:ModelInterface|ModelInterface]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#SVMGeneticInterface|SVMGeneticInterface]]">
<Option key="creationFcn" value="createInitialPopulation"/>
<Option key="crossoverFcn" value="simpleCrossover"/>
<Option key="mutationFcn" value="simpleMutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="backend" value="libSVM"/>
<Option key="type" value="epsilon-SVR"/>
<Option key="kernel" value="rbf"/>
<Option key="kernelParamBounds" value="-4,4"/>
<Option key="regParamBounds" value="-5,5"/>
<Option key="nu" value="0.01"/>
<Option key="epsilon" value="0"/>
<Option key="stoppingTolerance" value="1e-5"/>
</[[Config:ModelInterface|ModelInterface]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#RationalGeneticInterface|RationalGeneticInterface]]">
<Option key="crossoverFcn" value="crossover"/>
<Option key="mutationFcn" value="mutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="creationFcn" value="initial"/>
<Option key="weightBounds" value="1,40"/>
<Option key="percentBounds" value="1,100"/>
<Option key="percentRational" value="70"/>
<Option key="frequencyVariable" value="off"/>
<Option key="basis" value="chebyshev"/>
</[[Config:ModelInterface|ModelInterface]]>
<[[Config:ModelInterface|ModelInterface]] type="[[ModelInterface#BFGeneticInterface|BFGeneticInterface]]">
<Option key="type" value="RBF"/>
<Option key="crossoverFcn" value="crossover"/>
<Option key="mutationFcn" value="mutation"/>
<Option key="constraintFcn" value="[]"/>
<Option key="creationFcn" value="initial"/>
<[[Config:BasisFunction|BasisFunction]] name="gaussian" min=".1" max="5" scale="log"/>
<[[Config:BasisFunction|BasisFunction]] name="multiquadric" min=".1" max="5" scale="log"/>
<[[Config:BasisFunction|BasisFunction]] name="exponential" min=".1,.5" max="5,2" scale="log,lin"/>
<Option key="regression" value="-1,0,1,2"/>
<Option key="backend" value="Direct"/>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:ModelInterface|ModelInterface]]>
</[[Config:AdaptiveModelBuilder|AdaptiveModelBuilder]]>
