C++ API Reference for Intel® Data Analytics Acceleration Library 2019

References | Namespaces | Classes | Enumerations
Local Response Normalization Layer

Contains classes for local response normalization layer. More...

References

 Backward Local Response Normalization Layer
 Contains classes for the backward local response normalization layer.
 
 Forward Local Response Normalization Layer
 Contains classes for the forward local response normalization layer.
 

Namespaces

 daal::algorithms::neural_networks::layers::lrn
 Contains classes for local response normalization layer.
 
 daal::algorithms::neural_networks::layers::lrn::interface1
 Contains version 1.0 of Intel(R) Data Analytics Acceleration Library (Intel(R) DAAL) interface.
 

Classes

class  Batch< algorithmFPType, method >
 Provides methods for the local response normalization layer in the batch processing mode. More...
 
class  Parameter
 Parameters for the local response normalization layer. More...
 

Enumerations

enum  Method { defaultDense = 0 }
 Computation methods for the local response normalization layer. More...
 
enum  LayerDataId { auxData = layers::lastLayerInputLayout + 1, auxSmBeta }
 Identifiers of input objects for the backward stage and results for the forward stage of the local response normalization layer. More...
 

Enumeration Type Documentation

enum LayerDataId

Enumerator
auxData 

Data processed at the forward stage of the layer

auxSmBeta 

Pointer to the tensor of size n1 x n2 x ... x np, that stores value of (kappa + alpha * sum((x_i)^2))^(-beta)

enum Method

Enumerator
defaultDense 

Default: performance-oriented method

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