Home » Microsoft » DP-100 » Which normalization type should you use?
You need to implement a scaling strategy for the local penalty detection data.
Which normalization type should you use?
A. Streaming
B. Weight
C. Batch
D. Cosine
Correct Answer: C
Explanation/Reference:
Post batch normalization statistics (PBN) is the Microsoft Cognitive Toolkit (CNTK) version of how to evaluate the population mean and variance of Batch Normalization which could be used in inference Original Paper.
In CNTK, custom networks are defined using the BrainScriptNetworkBuilder and described in the CNTK network description language "BrainScript."
Scenario:
Local penalty detection models must be written by using BrainScript.
References:
https://docs.microsoft.com/en-us/cognitive-toolkit/post-batch-normalization-statistics