Developer Guide

Contents

Two-Dimensional Average Pooling Backward Layer

The forward two-dimensional (2D) average pooling layer is a form of non-linear downsampling of an input tensor
X
= (
x
(1)
...
x
(
p
)
) of size
n
1
x
n
2
x ... x
n
p
. For more details, see Forward 2D Average Pooling Layer. The backward 2D average pooling layer back-propagates the input gradient
G
= (
g
(1)
...
g
(
p
)
) of size
m
1
x
m
2
x ... x
m
p
computed on the preceding layer. The result of the backward 2D average pooling layer
Z
= (
z
(1)
...
z
(
p
)
) is the tensor of the same size
n
1
x
n
2
x ... x
n
p
as the input of the forward computation. The backward layer propagates the elements of the gradient multiplied by the coefficient 1/(
f
k
1
*
f
k
2
) to the corresponding pooled subtensors of the tensor
Z
:

Problem Statement

Given a
p
-dimensional tensor
G
R
n
1
x
n
2
x ... x
n
p
with the gradient computed on the preceding layer, the problem is to compute the
p
-dimensional tensor
Z
R
n
1
x
n
2
x ... x
n
p
with the result:

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