Note: This page has been translated by MathWorks. Click here to see

To view all translated materials including this page, select Country from the country navigator on the bottom of this page.

To view all translated materials including this page, select Country from the country navigator on the bottom of this page.

Evaluate cost function for samples

```
[y,info]
= sdo.evaluate(fcn,params)
```

```
[y,info]
= sdo.evaluate(fcn,params,param_samples)
```

```
[y,info]
= sdo.evaluate(___,opts)
```

`[`

evaluates
the cost function, `y`

,`info`

]
= sdo.evaluate(`fcn`

,`params`

)`fcn`

, for samples of the parameter
space specified by `params`

(`sdo.ParameterSpace`

object).
The software generates a table of samples with 2*Np*+1
rows and *Np* columns. These samples are generated
based on the parameter space specifications in `params`

,
per its `ParameterDistributions`

, `RankCorrelation`

,
and `Options`

properties. *Np* is
the number of parameters specified in `params`

. `fcn`

takes
sample values and computes model goal values. A model goal could be
a cost (objective), constraint, or assessment of difference between
experimental data and model simulation. `sdo.evaluate`

applies `fcn`

to
each row of the table of samples. `y`

is a table
with one column for each model goal output returned by `fcn`

and
2*Np*+1 rows. Additional evaluation information is
returned in `info`

.

`[`

evaluates
the cost function for the specified parameter samples table, `y`

,`info`

]
= sdo.evaluate(`fcn`

,`params`

,`param_samples`

)`param_samples`

.
For this syntax, you can specify `params`

as an `sdo.ParameterSpace`

object
or a vector of `param.Continuous`

objects. `y`

is
a table with one column for each model goal (cost or constraint) output
returned by `fcn`

. `y`

contains
as many rows as `param_samples`

.

`sdo.EvaluateOptions`

| `sdo.ParameterSpace`

| `sdo.analyze`

| `sdo.optimize`

| `sdo.sample`