---
title: "applyBackward(batchSize:inputA:inputB:inputC:output:outputGradient:generatingInputAGradient:generatingInputBGradient:generatingInputCGradient:)"
framework: accelerate
role: symbol
role_heading: Instance Method
path: "accelerate/bnns/ternaryarithmeticlayer/applybackward(batchsize:inputa:inputb:inputc:output:outputgradient:generatinginputagradient:generatinginputbgradient:generatinginputcgradient:)"
---

# applyBackward(batchSize:inputA:inputB:inputC:output:outputGradient:generatingInputAGradient:generatingInputBGradient:generatingInputCGradient:)

Applies the layer backward to generate input gradients.

## Declaration

```swift
func applyBackward(batchSize: Int, inputA: BNNSNDArrayDescriptor, inputB: BNNSNDArrayDescriptor, inputC: BNNSNDArrayDescriptor, output: BNNSNDArrayDescriptor, outputGradient: BNNSNDArrayDescriptor, generatingInputAGradient inputAGradient: BNNSNDArrayDescriptor, generatingInputBGradient inputBGradient: BNNSNDArrayDescriptor, generatingInputCGradient inputCGradient: BNNSNDArrayDescriptor) throws
```

## Parameters

- `batchSize`: The number of input-output pairs.
- `inputA`: The descriptor of the first input..
- `inputB`: The descriptor of the second input.
- `inputC`: The descriptor of the third input.
- `output`: The descriptor of the output.
- `outputGradient`: The descriptor of the output gradient.
- `inputAGradient`: The descriptor of the first input gradient.
- `inputBGradient`: The descriptor of the second input gradient.
- `inputCGradient`: The descriptor of the third input gradient.

## See Also

### Applying a Ternary Arithmetic Layer

- [apply(batchSize:inputA:inputB:inputC:output:)](accelerate/bnns/ternaryarithmeticlayer/apply(batchsize:inputa:inputb:inputc:output:).md)