Download as pdf or txt
Download as pdf or txt
You are on page 1of 4

Artificial intelligence - Azure - Machine Learning

- Select the option that represents the correct order of following tasks: (A)
Predictive Experiment (B) Training Experiment (C) Model Evaluation (D)
Data Preprocessing (E) API Publishing R : B,D,C,A,E
- Which of the following can be generally used to clean and prepare Big
Data? R: U-SQL
- What is the default Python package manager in case of Azure ML
Studio? R: Conda
- Docker helps in _______. R: Deployment
- Get the required size of a dataset from a large amount of accumulated

m
data is called ________. R: Statistical sampling

er as
co
- Reference data is _________. R: Additional application data for user

eH w
- Azure ML Studio provides us with ________ number of API keys. R: 2

o.
- Which of the following is a python REPL environment? R: Jupyter
Notebook rs e
ou urc
- Which of the following is advanced python package for computer vision?
R: opencv
o

- Data can be imported into ML Studio through ________. R: Azure


aC s

storage and user upload


vi y re

- In general, Linear Machine Learning Models are associated with


__________. R: fast training
Reference data can be fetched on demand using ___________. R: All
ed d

-
the option
ar stu

- SVM models, in general, are best known to be applied in the case of


__________. R: More features
is

- The process of determining the causes that play a role in House Price
Th

increase in a particular area to model a House Price predictor is called


___________. R: Featuring engineering
- If 'n' is the number of columns/inputs of a web service API, then n is
sh

___________. R: anynumber
- If training time can be traded for accuracy, we can use _____________.
R: Neural Networks

This study source was downloaded by 100000819919857 from CourseHero.com on 03-28-2021 20:54:55 GMT -05:00

https://www.coursehero.com/file/48606105/Artificial-intelligence-Azure-Machine-Learningdocx/
- Which of the following is the best model to predict the number of
earthquakes occurring at a place based on historical data? R: poisson
regression
- Which of the following is false about Train Data and Test Data in Azure
ML Studio? R: Train data and test data split should follow a thumb-rule
of 80 : 20
- Small Memory Foot print can be acquired through ______________. R:
Decision Jungle
- A K-Means Cluster is said to be well defined if the cluster is ________.
R: Ellipse
- Asynchronous predictions with Azure ML Studio can be achieved
through __________. R: batch API

m
- What is the output of Azure Data Factory pipeline that uses the

er as
AzureMLBatchExecution activity to retrain a model? R: model.i.learner

co
eH w
file
To retrain the predictive model and update the web service through

o.
-

rs e
Azure Data Factory, which of the datasets are required? R: An Azure
ou urc
Stotage blob for the output of an AzureMLUpdateResource activity
- Azure Data Factory can be linked with which of the following Storage
o

services? All the options


aC s

- What service can be used along with Azure ML Studio Services to


vi y re

predict Machine Failure in real-time through data collected from


sensors? R: Azure Stream analytics
- While processing stored data in big data scenario, what is the optimal
ed d

way to generate predictions? R: Asyncronous generation


ar stu

- You create an Azure Stream Analytics job in which you want to call an
Azure Machine Learning web service that is managed in a different
is

Azure subscription. What can be done to use the Machine Learning


Web service? Azure ML function is added to Stream analytics job,
Th

specifying the URL and key for the web service


- Select Azure Data Factory pipeline activity that retrieves predictions
sh

from an Azure Machine Learning web service. R:


azureMLBatchExecution
- Azure Data Factory can be linked with ________ service to manage big
data clusters on demand. R: HD insight

This study source was downloaded by 100000819919857 from CourseHero.com on 03-28-2021 20:54:55 GMT -05:00

https://www.coursehero.com/file/48606105/Artificial-intelligence-Azure-Machine-Learningdocx/
- Azure Data Factory is used to ____________. R: none of the options x
Provide pipeline for asynchronous prediction x
- A web service can be published as Classic or [New]. Does this make
any difference? R: Yes; in consuming web service.
- In comparison to Azure Machine Learning Service, Azure Machine
Learning Studio has ____________. R: Fewer open-source packages
support ALL THE OPTIONS
- A client application needs to fetch reference data based on customer
location and data is shared on multiple databases. Servicing the
application through a single prediction web service is possible through
______________. R: Parametrising Webservice URL
PARAMETRISING DATABASE LOCATION ANY OF THE OPTIONS

m
- In Azure Stream analytics, webservice is added as a ___________. R:

er as
job FUNCTION

co
eH w
- Log transform is used when __________. R: The negative parameter is
not valid

o.
- rs e
Data Visualization in Azure ML Studio is possible through ________. R:
ou urc
Import module and jupyter notebook BOTH INBUILT AND JUPYTER
NOTEBOOK
o

- An environment for working with Azure Machine Learning in an Azure


aC s

subscription does not automatically create ___________. R: A pricing


vi y re

plan x A web service A STORAGE ACCOUNT


- Predictive Experiment can be used directly after creating it from a
training experiment. Select the appropriate option as answer. R: true
ed d

changes can be done only for customisation of web service for client application. X True, but
ar stu

need chamges with data transformation FALSE, CHANGES MUST BE DONE TO


FACILITATE PROPER WEB SERVICE INPUTS/OUTPUTS. True, changes can be done
only for customisation of web service for client application.
is

- Mean variance Normalization is used in case when the parameter


distribution is __________. R: Bell Shaped Distribution x none of the
Th

options CONTINUOUS DISTRIBUTION SKEW DISTRIBUTION


- Quality of our classifier can be determined through _________. R: recall
sh

CONFUSION MATRIX ACCURACY


- Azure Webservice is based on ____________. R: REST API and Xml
Format x REST API and JSON Format all the options

This study source was downloaded by 100000819919857 from CourseHero.com on 03-28-2021 20:54:55 GMT -05:00

https://www.coursehero.com/file/48606105/Artificial-intelligence-Azure-Machine-Learningdocx/
- Simple way to explore multiple datafiles from a Big Data Job is
____________. R: Use Import DOWNLOADING THE FILE TO AZURE
STORAGE AND UPLOAD INTO WORKSPACE
- All our published web services can be considered as _________. R:
azure Resources x Azure App Services azure app
- When predicting if the patient has cancer or not, which parameter must
be given importance? R: Precision RECALL
- Average amount of money spent by a user at a Supermarket can be
predicted through ____________ . R: CLUSTERING
- To prevent running Import Data module each time, we run an
experiment, when data is imported from Azure Blob storage, we can use
_____________. R: Genetated results x CACHED RESULTS

m
- A 5GB data file attained from a U-SQL job can be used for a training

er as
experiment through __________. R: Statistical sampling AZURE BLOB

co
eH w
STORAGE
Age can be Normalised through _________. R: Zscore LOGNORMAL

o.
-
- rs e
Collaboration in Azure Machine Learning is possible through ________.
ou urc
R: invitation to Azure Subscription INVITATION TO AZURE
SUBSCRIPTION
o

- To retrain the predictive model and update the webservice through Azure Data Factory, which of
aC s

the datasets are required? ALL THE OPTIONS


vi y re

- Which of the following is false about Train Data and Test Data in Azure ML Studio _________?
Train data and Test data split should follow a thumb-rule of 80 : 20.
-
ed d
ar stu
is
Th
sh

This study source was downloaded by 100000819919857 from CourseHero.com on 03-28-2021 20:54:55 GMT -05:00

https://www.coursehero.com/file/48606105/Artificial-intelligence-Azure-Machine-Learningdocx/
Powered by TCPDF (www.tcpdf.org)

You might also like