---
title: "computeNormBackward(input:output:axes:outputGradient:generatingInputGradient:)"
framework: accelerate
role: symbol
role_heading: Type Method
path: "accelerate/bnns/computenormbackward(input:output:axes:outputgradient:generatinginputgradient:)"
---

# computeNormBackward(input:output:axes:outputGradient:generatingInputGradient:)

Backpropogates gradients for the compute norm function.

## Declaration

```swift
static func computeNormBackward(input: BNNSNDArrayDescriptor, output: BNNSNDArrayDescriptor, axes: [Int]? = nil, outputGradient: BNNSNDArrayDescriptor, generatingInputGradient inputGradient: BNNSNDArrayDescriptor) throws
```

## Parameters

- `input`: The descriptor of the input.
- `output`: The descriptor of the output.
- `axes`: The indices of the axes over which the function computes the norm. Set to nil to specify that the function computes the norm over the entire tensor.
- `outputGradient`: The descriptor of the output delta.
- `inputGradient`: The descriptor of the input delta.

## See Also

### Compute norm functions

- [computeNorm(input:output:axes:)](accelerate/bnns/computenorm(input:output:axes:).md)
- [BNNSComputeNorm(_:_:_:_:)](accelerate/bnnscomputenorm(_:_:_:_:).md)
- [BNNSComputeNormBackward(_:_:_:_:_:_:)](accelerate/bnnscomputenormbackward(_:_:_:_:_:_:).md)
- [BNNSNormType](accelerate/bnnsnormtype.md)