Main Content

nssTrainingOptions

Create training options object for neural state-space systems

Since R2022b

    Description

    Returns either an Adam, SGDM, RMSProp, or L-BFGS options set object to train an idNeuralStateSpace network using nlssest.

    adamOpts = nssTrainingOptions("adam") returns a default optimizer option set to train an idNeuralStateSpace object using the adaptive moment estimation solver. Use dot notation to access the object properties.

    example

    sgdmOpts = nssTrainingOptions("sgdm") returns a default optimizer option set to train an idNeuralStateSpace object using the stochastic gradient descent with momentum solver. Use dot notation to access the object properties.

    example

    rmspropOpts = nssTrainingOptions("rmsprop") returns a default optimizer option set to train an idNeuralStateSpace object using the root mean square propagation solver. Use dot notation to access the object properties.

    example

    lbfgsOpts = nssTrainingOptions("lbfgs") returns a default optimizer option set to train an idNeuralStateSpace object using the limited-memory Broyden-Fletcher-Goldfarb-Shanno solver. Use dot notation to access the object properties.

    example

    Examples

    collapse all

    Use nssTrainingOptions to return an options set object to train an idNeuralStateSpace system.

    adamOpts = nssTrainingOptions("adam")
    adamOpts = 
      nssTrainingADAM with properties:
    
                      UpdateMethod: "ADAM"
                         LearnRate: 1.0000e-03
               GradientDecayFactor: 0.9000
        SquaredGradientDecayFactor: 0.9990
                         MaxEpochs: 100
                     MiniBatchSize: 1000
                 LearnRateSchedule: "none"
               LearnRateDropFactor: 0.1000
               LearnRateDropPeriod: 10
                            Lambda: 0
                              Beta: 0
                           LossFcn: "MeanAbsoluteError"
                       PlotLossFcn: 1
                  ODESolverOptions: [1x1 idoptions.nssDLODE45]
                  InputInterSample: 'spline'
                        WindowSize: 2.1475e+09
                           Overlap: 0
    
    

    Use dot notation to access the object properties.

    adamOpts.PlotLossFcn = false;

    You can use adamOpts as an input argument to nlssest to specify the training options for the state or the non-trivial output network of an idNeuralStateSpace object.

    Use nssTrainingOptions to return an options set object to train an idNeuralStateSpace system.

    sgdmOpts = nssTrainingOptions("sgdm")
    sgdmOpts = 
      nssTrainingSGDM with properties:
    
               UpdateMethod: "SGDM"
                  LearnRate: 0.0100
                   Momentum: 0.9500
                  MaxEpochs: 100
              MiniBatchSize: 1000
          LearnRateSchedule: "none"
        LearnRateDropFactor: 0.1000
        LearnRateDropPeriod: 10
                     Lambda: 0
                       Beta: 0
                    LossFcn: "MeanAbsoluteError"
                PlotLossFcn: 1
           ODESolverOptions: [1x1 idoptions.nssDLODE45]
           InputInterSample: 'spline'
                 WindowSize: 2.1475e+09
                    Overlap: 0
    
    

    Use dot notation to access the object properties.

    sgdmOpts.LearnRate = 0.01;

    You can use sgdmOpts as an input argument to nlssest to specify the training options for the state or the non-trivial output network of an idNeuralStateSpace object.

    Use nssTrainingOptions to return an options set object to train an idNeuralStateSpace system.

    rmspropOpts = nssTrainingOptions("rmsprop")
    rmspropOpts = 
      nssTrainingRMSProp with properties:
    
                      UpdateMethod: "RMSProp"
                         LearnRate: 1.0000e-03
        SquaredGradientDecayFactor: 0.9000
                         MaxEpochs: 100
                     MiniBatchSize: 1000
                 LearnRateSchedule: "none"
               LearnRateDropFactor: 0.1000
               LearnRateDropPeriod: 10
                            Lambda: 0
                              Beta: 0
                           LossFcn: "MeanAbsoluteError"
                       PlotLossFcn: 1
                  ODESolverOptions: [1x1 idoptions.nssDLODE45]
                  InputInterSample: 'spline'
                        WindowSize: 2.1475e+09
                           Overlap: 0
    
    

    Use dot notation to access the object properties.

    rmspropOpts.PlotLossFcn = false;

    You can use rmspropOpts as an input argument to nlssest to specify the training options for the state or the non-trivial output network of an idNeuralStateSpace object.

    Use nssTrainingOptions to return an options set object to train an idNeuralStateSpace system.

    lbfgsOpts = nssTrainingOptions("lbfgs")
    lbfgsOpts = 
      nssTrainingLBFGS with properties:
    
                       UpdateMethod: "LBFGS"
                   LineSearchMethod: "weak-wolfe"
                      MaxIterations: 100
         MaxNumLineSearchIterations: 20
                        HistorySize: 10
        InitialInverseHessianFactor: 1
                  GradientTolerance: 1.0000e-06
                      StepTolerance: 1.0000e-06
                             Lambda: 0
                               Beta: 0
                            LossFcn: "MeanAbsoluteError"
                        PlotLossFcn: 1
                   ODESolverOptions: [1x1 idoptions.nssDLODE45]
                   InputInterSample: 'spline'
                         WindowSize: 2.1475e+09
                            Overlap: 0
    
    

    Use dot notation to access the object properties.

    lbfgsOpts.PlotLossFcn = false;

    You can use lbfgsOpts as an input argument to nlssest to specify the training options for the state or the non-trivial output network of an idNeuralStateSpace object.

    Output Arguments

    collapse all

    Adam options set object, specified as an nssTrainingADAM object.

    SGDM options set object, specified as an nssTrainingSGDM object.

    RMSProp options set object, specified as an nssTrainingRMSProp object.

    L-BFGS options set object, specified as an nssTrainingLBFGS object.

    Version History

    Introduced in R2022b