<!--
{
  "availability" : [
    "iOS: 17.0.0 -",
    "iPadOS: 17.0.0 -",
    "macCatalyst: 17.0.0 -",
    "macOS: 14.0.0 -",
    "tvOS: 17.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateMLComponents",
  "identifier" : "/documentation/CreateMLComponents/FullyConnectedNetworkMultiLabelClassifierModel",
  "metadataVersion" : "0.1.0",
  "role" : "Structure",
  "symbol" : {
    "kind" : "Structure",
    "modules" : [
      "Create ML Components"
    ],
    "preciseIdentifier" : "s:18CreateMLComponents46FullyConnectedNetworkMultiLabelClassifierModelV"
  },
  "title" : "FullyConnectedNetworkMultiLabelClassifierModel"
}
-->

# FullyConnectedNetworkMultiLabelClassifierModel

A multi-label classifier model that uses a fully-connected network.

```
struct FullyConnectedNetworkMultiLabelClassifierModel<Scalar, Label> where Scalar : MLShapedArrayScalar, Scalar : BinaryFloatingPoint, Label : Comparable, Label : Decodable, Label : Encodable, Label : Hashable
```

## Topics

### Performing a classification

[`func applied(to: MLShapedArray<Scalar>, eventHandler: EventHandler?) throws -> ClassificationDistribution<Label>`](/documentation/CreateMLComponents/FullyConnectedNetworkMultiLabelClassifierModel/applied(to:eventHandler:))

Performs a classification on a shaped array.

### Computing evaluation metrics

[`func evaluation(on: some Collection<AnnotatedFeature<MLShapedArray<Scalar>, Set<Label>>>, confidenceThresholds: [Label : Float]) throws -> MultiLabelClassificationMetrics<Label>`](/documentation/CreateMLComponents/FullyConnectedNetworkMultiLabelClassifierModel/evaluation(on:confidenceThresholds:))

Computes evaluation metrics on annotated examples.

### Performing a prediction

[`func prediction(from:confidenceThresholds:)`](/documentation/CreateMLComponents/FullyConnectedNetworkMultiLabelClassifierModel/prediction(from:confidenceThresholds:))

Performs a prediction and keeps label-confidence pairs that are greater than or equal to the provided
confidence thresholds.

### Updating the precision recall curve

[`func updatePrecisionRecallCurves(some Collection<AnnotatedFeature<MLShapedArray<Scalar>, Set<Label>>>) async throws`](/documentation/CreateMLComponents/FullyConnectedNetworkMultiLabelClassifierModel/updatePrecisionRecallCurves(_:))

Updates the per-label precision-recall curve using the input data.

## Relationships

### Conforms To

[`CustomDebugStringConvertible`](/documentation/Swift/CustomDebugStringConvertible)

[`Copyable`](/documentation/Swift/Copyable)

[`SendableMetatype`](/documentation/Swift/SendableMetatype)

[`Decodable`](/documentation/Swift/Decodable)

[`Encodable`](/documentation/Swift/Encodable)

[`Sendable`](/documentation/Swift/Sendable)

[`Transformer`](/documentation/CreateMLComponents/Transformer)

[`Escapable`](/documentation/Swift/Escapable)

---

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)