<!--
{
  "availability" : [
    "macOS: 11.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/ClassifierType/multilayerPerceptron(layerSizes:)",
  "metadataVersion" : "0.1.0",
  "role" : "Case",
  "symbol" : {
    "kind" : "Case",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML17MLSoundClassifierV15ModelParametersV0D4TypeO20multilayerPerceptronyAGSaySiG_tcAGmF"
  },
  "title" : "MLSoundClassifier.ModelParameters.ClassifierType.multilayerPerceptron(layerSizes:)"
}
-->

# MLSoundClassifier.ModelParameters.ClassifierType.multilayerPerceptron(layerSizes:)

A neural network model that uses three or more layers to classify an input into a category.

```
case multilayerPerceptron(layerSizes: [Int])
```

## Parameters

`layerSizes`

An array of positive integers. Each element represents the number of units for that hidden
layer.

## Discussion

The neural network has a minimum of three layers:

- An input layer
- One or more hidden layers
- An output layer

The number of integers in your `layerSizes` array determines the number of hidden layers in the neural
network. Each integer in the array determines the size of that hidden layer.

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)