<!--
{
  "availability" : [
    "iOS: 14.0.0 - 18.0.0",
    "iPadOS: 14.0.0 - 18.0.0",
    "macCatalyst: 14.0.0 - 18.0.0",
    "macOS: 11.0.0 - 15.0.0",
    "tvOS: 14.0.0 - 18.0.0",
    "visionOS: 1.0.0 - 2.0.0",
    "watchOS: 7.0.0 - 11.0.0"
  ],
  "documentType" : "symbol",
  "framework" : "Accelerate",
  "identifier" : "/documentation/Accelerate/BNNSOptimizerAdamFields",
  "metadataVersion" : "0.1.0",
  "role" : "Structure",
  "symbol" : {
    "kind" : "Structure",
    "modules" : [
      "Accelerate"
    ],
    "preciseIdentifier" : "c:@SA@BNNSOptimizerAdamFields"
  },
  "title" : "BNNSOptimizerAdamFields"
}
-->

# BNNSOptimizerAdamFields

A structure that contains the fields of an Adam optimizer.

```
struct BNNSOptimizerAdamFields
```

## Topics

### Initializers

[`init(learning_rate:beta1:beta2:time_step:epsilon:gradient_scale:regularization_scale:clip_gradients:clip_gradients_min:clip_gradients_max:regularization_func:)`](/documentation/Accelerate/BNNSOptimizerAdamFields/init(learning_rate:beta1:beta2:time_step:epsilon:gradient_scale:regularization_scale:clip_gradients:clip_gradients_min:clip_gradients_max:regularization_func:))

Returns a new Adam optimizer fields structure from the specified parameters.

[`init()`](/documentation/Accelerate/BNNSOptimizerAdamFields/init())

Returns a new Adam optimizer fields structure.

### Instance Properties

[`learning_rate`](/documentation/Accelerate/BNNSOptimizerAdamFields/learning_rate)

A value that specifies the learning rate.

[`beta1`](/documentation/Accelerate/BNNSOptimizerAdamFields/beta1)

A value that specifies the first moment constant in the range 0 to 1.

[`beta2`](/documentation/Accelerate/BNNSOptimizerAdamFields/beta2)

A value that specifies the second moment constant in the range 0 to 1.

[`time_step`](/documentation/Accelerate/BNNSOptimizerAdamFields/time_step)

A value that represents the optimizer’s current time and you’re responsible for updating after optimizing all the layer parameters in your network.

[`epsilon`](/documentation/Accelerate/BNNSOptimizerAdamFields/epsilon)

An addition for the division in the parameter update stage.

[`gradient_scale`](/documentation/Accelerate/BNNSOptimizerAdamFields/gradient_scale)

A value that specifies the gradient scaling factor.

[`regularization_scale`](/documentation/Accelerate/BNNSOptimizerAdamFields/regularization_scale)

A value that specifies the regularization scaling factor.

[`clip_gradients`](/documentation/Accelerate/BNNSOptimizerAdamFields/clip_gradients)

A Boolean value that specifies whether to clip the gradient between minimum and maximum values.

[`clip_gradients_min`](/documentation/Accelerate/BNNSOptimizerAdamFields/clip_gradients_min)

The values for the minimum gradient.

[`clip_gradients_max`](/documentation/Accelerate/BNNSOptimizerAdamFields/clip_gradients_max)

The values for the maximum gradient.

[`regularization_func`](/documentation/Accelerate/BNNSOptimizerAdamFields/regularization_func)

The variable that specifies the regularization function.


---

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)