Batch Processing

Layer Input

The backward local response normalization layer accepts the input described below. Pass the Input ID as a parameter to the methods that provide input for your algorithm. For more details, see Algorithms.

Input ID

Input

inputGradient

Pointer to the tensor of size n1 x n2 x ... x np that stores the input gradient computed on the preceding layer. This input can be an object of any class derived from Tensor.

inputFromForward

Collection of input data needed for the backward local response normalization layer. This collection can contain objects of any class derived from Tensor.

Element ID

Element

auxData

Pointer to the tensor of size n1 x n2 x ... x np that stores the input data for the forward local response normalization layer. This input can be an object of any class derived from Tensor.

auxSmBeta

Pointer to the tensor of size n1 x n2 x ... x np that stores the value of (sk * (ik))-β . This input can be an object of any class derived from Tensor.

Layer Parameters

For common parameters of neural network layers, see Common Parameters.

In addition to the common parameters, the backward local response normalization layer has the following parameters:

Parameter

Default Value

Description

algorithmFPType

float

The floating-point type that the algorithm uses for intermediate computations. Can be float or double.

method

defaultDense

Computation method used by the algorithm. The only method supported by the layer so far is acrossDimension.

dimension

1

Numeric table of size 1 x 1 with the dimension index of type size_t to calculate local response normalization backpropagation.

kappa

2

Value of layer hyper-parameter κ.

alpha

1.0e-04

Value of layer hyper-parameter α.

beta

0.75

Value of layer hyper-parameter β.

nAdjust

5

Value of layer hyper-parameter n.

Layer Output

The backward local response normalization layer calculates the result described below. Pass the Result ID as a parameter to the methods that access the results of your algorithm. For more details, see Algorithms.

Result ID

Result

gradient

Pointer to the tensor of size n1 x n2 x ... x np that stores the result of the backward local response normalization layer. This input can be an object of any class derived from Tensor.

For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)