WOLFRAM

Wolfram Language & System Documentation Center

PerceptronNetModel[]

represents a perceptron net for prediction.

PerceptronNetModel[hpars]

uses the custom hyperparameters hpars.

PerceptronNetModel[hpars,vars]

use the provided variables vars.

Details
Hyperparameters
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Hyperparameters  
"Depth"  
"Width"  
"Activation"  
Variables  
Evaluation  
Information  
Fitting  
See Also
History
Cite this Page

PerceptronNetModel

PerceptronNetModel[]

represents a perceptron net for prediction.

PerceptronNetModel[hpars]

uses the custom hyperparameters hpars.

PerceptronNetModel[hpars,vars]

use the provided variables vars.

Details

  • PerceptronNetModel models a classification or regression task as a multilayer perceptron neural net.

    • Hyperparameters

  • The following hyperparameters may be specified to control the perceptron net:
  • "Depth"2number of layers
    "Width"10size of the layers
    "Activation"Tanhlayer specification
  • Deeper models can learn more complex, hierarchical patterns by building up abstractions layer by layer but require more data and training time. "Depth" can be increased when hierarchical structure in relationships between variables is suspected.
  • Wider models can capture more variation and nuances in the data at each level of abstraction but use more parameters and memory. "Width" can be increased when there are many samples and there is need to capture more complex patterns at each level.

Examples

open all close all

Basic Examples  (3)

Create a generic perceptron net model:

Specify multiple custom hyperparameters:

Train a net on the Fisher Iris dataset:

Extract the net model:

Scope  (15)

Hyperparameters  (3)

"Depth"  (1)

Define a net with a default "Depth" value:

Specify a custom value:

"Width"  (1)

Specify a wider net:

"Activation"  (1)

Specify a different activation function:

Variables  (3)

Define a net with a specific number of variables:

Use explicit variable names:

ModelFit will assume the number of variables is one less than the dimensionality of data points:

Evaluation  (3)

Evaluate a trained perceptron net model numerically:

Evaluate the net on a list of inputs:

Perceptron nets cannot be evaluated symbolically:

Information  (5)

View general information about a model:

Some information is only available when variables or parameters are fully specified:

Extract a single property:

Retrieve multiple properties:

Get information about the default model values:

Fitting  (1)

Fit a perceptron net model with the default hyperparameters:

Wolfram Research (2026), PerceptronNetModel, Wolfram Language function, https://reference.wolfram.com/language/ref/PerceptronNetModel.html.

Text

Wolfram Research (2026), PerceptronNetModel, Wolfram Language function, https://reference.wolfram.com/language/ref/PerceptronNetModel.html.

CMS

Wolfram Language. 2026. "PerceptronNetModel." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/PerceptronNetModel.html.

APA

Wolfram Language. (2026). PerceptronNetModel. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/PerceptronNetModel.html

BibTeX

@misc{reference.wolfram_2026_perceptronnetmodel, author="Wolfram Research", title="{PerceptronNetModel}", year="2026", howpublished="\url{https://reference.wolfram.com/language/ref/PerceptronNetModel.html}", note=[Accessed: 22-July-2026]}

BibLaTeX

@online{reference.wolfram_2026_perceptronnetmodel, organization={Wolfram Research}, title={PerceptronNetModel}, year={2026}, url={https://reference.wolfram.com/language/ref/PerceptronNetModel.html}, note=[Accessed: 22-July-2026]}