AZURE ML 1.Quality of our classifier can be determined through...

AZURE ML

1.Quality of our classifier can be determined through _________.

Confusion Matrix

Accuracy

Precision

Recall

2.Which of the following can be generally used to clean and prepare Big Data?

Data Warehouse

Pandas

U-SQL

Data Lake

3. Average amount of money spent by a user at a Supermarket can be predicted through ____________ .

Regression

Classification

Clustering

None of the options

4. 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 ______________.

Parametrising Database Connection

Parametrising Webservice URL

Any of the options

Parametrising Database location

5. Get the required size of a dataset from a large amount of accumulated data is called ________.

Preprocess Sampling

Statistical Sampling

Rational Sampling

Preperation Sampling

6. A web service can be published as Classic or [New]. Does this make any difference?

Yes; in consuming web service.

No change, except for pricing plan.

No change, except for versioning.

Yes; in managing web service.

7. When predicting if the patient has cancer or not, which parameter must be given importance?

Threshold

Accuracy

Recall

Precision

8. Data Visualization in Azure ML Studio is possible through ________.

Import module and jupyter notebook

Both inbuilt and jupyter notebook

Import module

In-built visualisation options

Jupyter Notebook

9. Select Azure Data Factory pipeline activity that retrieves predictions from an Azure Machine Learning web service.

AzureUpdateResource

AzureBlob

AzureMLBatchExecution

AzureMLBatchProcessing

10. An environment for working with Azure Machine Learning in an Azure subscription does not automatically create ___________.

A workspace

A web service

A storage account

A pricing plan

11. Collaboration in Azure Machine Learning is possible through ________.

Invitation to Azure Subscription

Invitation to Workspace

Collaboration is not possible

Merging Workspaces

12. If training time can be traded for accuracy, we can use _____________.

Decision Forest

Neural Networks

Logistic Regression

Boosted Decision Tree

13. A K-Means Cluster is said to be well defined if the cluster is ________.

Polygon with cluster number of edges

Ellipse

No such metric

Circle

14. All our published web services can be considered as _________.

Azure Resources

None of the options

Azure App Services

Azure Apps

15. 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

B , D, C, A, E

D, B, C, A, E

A, B, C, D, E

B, C, D, A, E

16. What is the output of Azure Data Factory pipeline that uses the AzureMLBatchExecution activity to retrain a model?

prediction file

model.ilearner file

training data file

All the options

17. Age can be Normalised through _________.

LogNormal

Logistic

MinMax

Zscore

18. Mean variance Normalization is used in case when the parameter distribution is __________.

Bell shaped Distribution

None of the options

Continuous Distribution

Skew Distribution

19. Predictive Experiment can be used directly after creating it from a training experiment. Select the appropriate option as answer.

True, but need changes 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.

False, a new predictive experiment must be created from scratch.

20. Azure Webservice is based on ____________.

SOAP API and JSON Format

REST API and JSON Format

All the options

REST API and Xml Format