Developer Guide

Contents

Dropout Backward Layer

The dropout activation layer applies the transform
y
=
B
(
r
) *
x
/
r
to the input data, where
B
(
r
) is a Bernoulli random variable with parameter
r
. For more details, see the forward dropout layer. The backward dropout layer computes value
z
=
B
(
r
) *
g
/
r
.

Problem Statement

Given a
p
-dimensional tensor
G
=
g
i
1
...
i
p
and
M
=
m
i
1
...
i
p
of size
n
1
x
n
2
x ... x
n
p
, the problem is to compute a
p
-dimensional tensor
Z
= (
z
i
1
...
i
p
) of size
n
1
x
n
2
x ... x
n
p
, where:
z
i
1
...
i
p
=
m
i
1
...
i
p
*
g
i
1
...
i
p

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