<!--
{
  "availability" : [
    "iOS: 16.0.0 -",
    "iPadOS: 16.0.0 -",
    "macCatalyst: 16.0.0 -",
    "macOS: 13.0.0 -",
    "tvOS: 16.0.0 -",
    "visionOS: 1.0.0 -",
    "watchOS: 11.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateMLComponents",
  "identifier" : "/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration",
  "metadataVersion" : "0.1.0",
  "role" : "Structure",
  "symbol" : {
    "kind" : "Structure",
    "modules" : [
      "Create ML Components"
    ],
    "preciseIdentifier" : "s:18CreateMLComponents34FullyConnectedNetworkConfigurationV"
  },
  "title" : "FullyConnectedNetworkConfiguration"
}
-->

# FullyConnectedNetworkConfiguration

A fully connected network configuration.

```
struct FullyConnectedNetworkConfiguration
```

## Topics

### Creating a network configuration

[`init()`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/init())

Creates a default fully-connected-network configuration.

### Getting the properties

[`batchSize`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/batchSize)

The number of examples to use per mini-batch.

[`dropoutProbability`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/dropoutProbability)

The dropout probability.

[`earlyStopIterationCount`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/earlyStopIterationCount)

The number of iterations to use when evaluating whether to stop early.

[`earlyStoppingTolerance`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/earlyStoppingTolerance)

The early-stopping tolerance.

[`hiddenUnitCounts`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/hiddenUnitCounts)

The number of neurons in each hidden layer.

[`learningRate`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/learningRate)

The learning rate.

[`maximumIterations`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/maximumIterations)

The maximum number of iterations.

[`randomSeed`](/documentation/CreateMLComponents/FullyConnectedNetworkConfiguration/randomSeed)

A seed to generate reproducible results from random operations such as column and row subsampling.

## Relationships

### Conforms To

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

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

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

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

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

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

---

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)