DAS632 Quiz2

You are building an AI solution that will use Sentiment Analysis results from surveys to calculate bonuses for customer service staff.
You need to ensure that the solution meets the Microsoft responsible AI principles.
What should you do?

• Publish the raw survey data to a central location and provide the staff with access to the location

• Use all the surveys, including surveys by customers who requested that their account be deleted and their data be removed.

• Include the Sentiment Analysis results when surveys return a low confidence score.

• Add a human review and approval step before making decisions that affect the staff's financial situation.

You have an Azure subscription that contains a Language service resource named ta1 and a virtual network named vnet1.
You need to ensure that only resources in vnet1 can access ta1.
What should you configure?

• a network security group (NSG) for vnet1

• Azure Firewall for vnet1

• the virtual network settings for ta1

• a Language service container for ta1

You are developing a monitoring system that will analyze engine sensor data, such as rotation speed, angle, temperature, and pressure. The system must generate an alert in response to atypical values.
What should you include in the solution?

• Univariate Anomaly Detection

• Multivariate Anomaly Detection

• metric alerts in Azure Monitor

• Application Insights in Azure Monitor

You have an app named App1 that uses an Azure Cognitive Services model to identify anomalies in a time series data stream.
You need to run App1 in a location that has limited connectivity. The solution must minimize costs.
What should you use to host the model?

• Azure Kubernetes Service (AKS)

• Azure Container Instances

• a Kubernetes cluster hosted in an Azure Stack Hub integrated system

• the Docker Engine

You are building a solution that will detect anomalies in sensor data from the previous 24 hours.
You need to ensure that the solution scans the entire dataset, at the same time, for anomalies.
Which type of detection should you use?

• azure apache

• change points

• streaming

• batch

You have an Azure subscription that contains an Anomaly Detector resource.
You deploy a Docker host server named Server1 to the on-premises network.
You need to host an instance of the Anomaly Detector service on Server1.
Which parameter should you include in the docker run command?

• Fluentd

• Mounts

• Http Proxy

• Billing

You have an Azure Video Analyzer for Media (previously Video Indexer) service that is used to provide a search interface over company videos on your company's website.
You need to be able to search for videos based on who is present in the video.
What should you do?

• Create person objects and provide face images for each object.

• Create a person model and associate the model to the videos.

• Invite the entire staff of the company to Video Indexer.

• Edit the faces in the videos.

• Upload names to a language model.

You use the Custom Vision service to build a classifier.
After training is complete, you need to evaluate the classifier.
Which two metrics are available for review? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.

• F-score

• recall

• precision

• area under the curve (AUC)

• weighted accuracy

You have the following Python function for creating Azure Cognitive Services resources programmatically. def create_resource (resource_name, kind, account_tier, location) : parameters = CognitiveServicesAccount(sku=Sku(name=account_tier), kind=kind, location=location, properties={}) result = client.accounts.create(resource_group_name, resource_name, parameters)
You need to call the function to create a free Azure resource in the West US Azure region. The resource will be used to generate captions of images automatically.
Which code should you use?

• create_resource("res1", "ComputerVision", "F0", "westus")

• create_resource("res1", "CustomVision.Prediction", "F0", "westus")

• create_resource("res1", "ComputerVision", "S0", "westus")

• create_resource("res1", "CustomVision.Prediction", "S0", "westus")

You need to build a solution that will use optical character recognition (OCR) to scan sensitive documents by using the Computer Vision API. The solution must
NOT be deployed to the public cloud.
What should you do

• Build an on-premises web app to query the Computer Vision endpoint.

• Host the Computer Vision endpoint in a container on an on-premises server.

• Host an exported Open Neural Network Exchange (ONNX) model on an on-premises server.

• Build an Azure web app to query the Computer Vision endpoint.