Developer Guide

Contents

Common Parameters

Neural network layers have the following common parameters:
Parameter
Default Value
Description
weights
Initializer
services::SharedPtr <initializers:: InitializerIface> (new initializers::uniform:: Batch<>())
Weights initializer for the layer.
biases
Initializer
services::SharedPtr <initializers:: InitializerIface> (new initializers::uniform:: Batch<>())
Biases initializer for the layer.
predictionStage
false
A flag that specifies whether the layer is used at the prediction stage. Applies to forward layers.
weightsAndBiases
Initialized
false
Initialization status of weights and biases:
  • true
    if the user provides weights and biases. It is your responsibility to set the flag to
    true
    so that the layer uses the user-defined weights and biases.
  • false
    if the layer uses the default initializer or the one selected by the user from the list of supported initializers to initialize weights and biases.

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