Developer Guide

Contents

Batch Processing

Layer Input

The backward one-dimensional max pooling 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 tensor
G
of size
l
1
x ... x
l
p
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 data needed for the backward one-dimensional max pooling layer.
Element ID
Element
auxSelectedIndices
Tensor
T
of size
l
1
x ... x
l
p
that stores indices of maximum elements.
auxInputDimensions
NumericTable of size 1 x
p
that stores the sizes of the dimensions of input data tensor
X
:
n
1
,
n
2
, …,
n
p
.

Layer Parameters

For common parameters of neural network layers, see Common Parameters.
In addition to the common parameters, the backward one-dimensional max pooling 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
Performance-oriented computation method, the only method supported by the layer.
kernelSize
KernelSize(2)
Data structure representing the size of the one-dimensional subtensor from which the maximum element is selected.
stride
Stride(2)
Data structure representing the interval on which the subtensors for max pooling are selected.
padding
Padding(0)
Data structure representing the number of data elements to implicitly add to each side of the one-dimensional subtensor along which max pooling is performed.
index
Index(p-1)
Index
k
of the dimension along which max pooling is performed.

Layer Output

The backward one-dimensional max pooling 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 tensor
Z
of size
n
1
x ... x
n
p
that stores the result of the backward one-dimensional max pooling layer. This input can be an object of any class derived from
Tensor
.

Product and Performance Information

1

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804