C++ API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1

Namespaces | Enumerations
daal::algorithms::neural_networks::layers::dropout Namespace Reference

Contains classes for dropout layer.

Namespaces

 backward
 Contains classes for the backward dropout layer.
 
 forward
 Contains classes for the forward dropout layer.
 
 interface1
 Contains version 1.0 of Intel(R) Data Analytics Acceleration Library (Intel(R) DAAL) interface.
 

Enumerations

enum  Method { defaultDense = 0 }
 Computation methods for the dropout layer. More...
 
enum  LayerDataId { auxRetainMask = layers::lastLayerInputLayout + 1 }
 Identifiers of input objects for the backward dropout layer and results for the forward dropout layer. More...
 

Enumeration Type Documentation

Enumerator
auxRetainMask 

Tensor filled with Bernoulli random variates (0 in positions that are dropped, 1 - in the others) divided by probability that any particular element is retained.

enum Method

Enumerator
defaultDense 

Default: performance-oriented method

For more complete information about compiler optimizations, see our Optimization Notice.