new | name of existing table

Array of activation functions to use for each layer. Choose from none, relu, elu, sigmoid, and tanh.

Surrogate evaluations for optimization, when gpadpoptmethod is set to montecarlo.

Compute and build surrogate model (recompute), or improve and build it (append).

Set to true if the input parameters are correlated.

Type of covariance function to use when surrogatemodel is set to gp. Use se for Squared exponential, matern32 for Matérn 3/2, matern52 for Matérn 5/2 and nn for Single-layer neural network.

string array with keys col1, col2, col3, … and values uniform, normal, lognormal, gamma, beta, weibull, or gumbel

Use immediate to stop immediately if there is an error, or use later to skip problematic parameters.

string map with keys 1, 2, 3, … and values embedded or external

string array with keys 1, 2, 3, … and valid filenames for the values

string array with keys 1, 2, 3, … and valid function names for the values

string array with keys 1, 2, 3, … and values none or name of existing geometry sampling node

string array with keys 1, 2, 3, … and values new or name of existing function

Deep Neural Network function to use, when surrogatemodel is set to dnn for each quantity of interest as an alternating array of keys and values.

string array with keys 1, 2, 3, … and values new or name of existing function

Gaussian Process function to use, when surrogatemodel is set to gp for each quantity of interest as an alternating array of keys and values.

string array with keys 1, 2, 3, … and values new or name of existing function

Least-Squares Fit function to use, when surrogatemodel is set to lsq for each quantity of interest as an alternating array of keys and values.

string array with keys 1, 2, 3, … and values new or name of existing function

Polynomial Chaos Expansion (PCE) function to use, when surrogatemodel is set to pce for each quantity of interest as an alternating array of keys and values.

Optimization method for error estimation, when surrogatemodel is set to gp.

string matrix of on or off

string array with keys 1, 2, 3, … and values sum, min, max, last, first, all, or interp (time-dependent study only)

string array with keys 1, 2, 3, … and interpolation time expressions for values

The interpolation times to sample for when innermostparameter is set to interp for each quantity of interest as an alternating array of keys and values.

Keep only last or all model evaluations in memory.

Array of dense and input for the first (input) layer

string array with keys col1, col2, col3, … and values between 0 and 1 as strings

The lower bound for the CDF for each input parameter distribution if lcdfselection is set to manual as an alternating array of keys and values.

string array with keys col1, col2, col3, … and values 0.3, 0.1, 0.01, 1e-3, 1e-4, 1e-5, 1e-6, 1e-7, or manual

Maximum surrogate evaluations for optimization, when gpadpoptmethod is set to direct.

Maximum number of optimization iterations, when gpadpoptmethod is set to direct.

Defines the overall trend of the trained function(s) when surrogatemodel is set to gp.

Number of input points when computeaction is set to recompute.

Number of input points when computeaction is set to append.

new | name of table group

The output table group, when surrogatemodel is set to none.

string array with keys 1, 2, 3, … and values new or name of existing table

Output table to use, when surrogatemodel is set to none for each quantity of interest as an alternating array of keys and values.

string matrix of last or all

PCE settings method. If set to auto (the default), the training will automatically determine the required polynomial degree needed to obtain suitable accuracy. If set to manual, the maximum polynomial degree is determined by the polydegreespce and qnorm settings.

Maximum polynomial degree, when pcesettings is set to manual.

string array with keys col1, col2, col3, … and units for the values

string array with keys 1, 2, 3, … and values reduce or configure

For each quantity of interest, specify if it is global (reduce) or nonglobal (configure) as an array of alternating keys and values.

string array with keys 1, 2, 3, … and values auto, sum, min, max, last, or first.

string array with keys 1, 2, 3, … and values sum, min, or max.

Q norm, when pcesettings is set to manual.

Initial random seed when useseed is set to manual.

string array with keys col1, col2, col3, … and double values as strings

string array with keys col1, col2, col3, … and double values as strings

Use gp (Gaussian Process), pce (Polynomial Chaos Expansion), dnn (Deep Neural Network), or lsq (Least-squares fit) to set up surrogate models after the design of experiments, or use none if no surrogate models should be created.

string array with keys col1, col2, col3, … and values between 0 and 1 as strings

The upper bound for the CDF for each input parameter distribution if ucdfselection is manual as an alternating array of keys and values.

string array with keys col1, col2, col3, … and values 0.7, 0.9, 0.99, 1-1e-3, 1-1e-4, 1-1e-5, 1-1e-6, 1-1e-7, or manual