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








 

Suggested Answer: C

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.
Reference:
https://docs.microsoft.com/en-us/cognitive-toolkit/post-batch-normalization-statistics

This question is in DP-100 Exam
For getting Microsoft Azure Data Scientist Associate Certificate


Disclaimers:
The website is not related to, affiliated with, endorsed or authorized by Microsoft. 
The website does not contain actual questions and answers from Microsoft's Certification Exams.
Trademarks, certification & product names are used for reference only and belong to Microsoft.