Microsoft AI Classroom Series Assessment Answers 2023

Here you will find Microsoft AI Classroom Series Assessment Answers. The Microsoft AI Classroom series is a certification initiative launched by Microsoft in association with Nasscom FutureSkills. The aim of this initiative is to upskill students and develop future developers on multiple emerging technologies.

Microsoft AI classroom series assessment is an AI course for beginners which is available for free to all. If you’re looking for a free AI course for beginners, Microsoft is one of the best options available out there.

Microsoft AI Classroom Series Assessment Answers 2023

Following are Microsoft AI Classroom Series Assessment MCQs with Answers.

1) You want to use automated machine learning to train a regression model with the best possible R2 score. How should you configure the automated machine learning experiment?

Answer: Set the Primary metric to R2 score

2) You want to use the Computer Vision service to analyze images. You also want to use the Text Analytics service to analyze text. You want developers to require only one key and endpoint to access all of your services. What kind of resource should you create in your Azure subscription?

Answer: Cognitive Services

3) You want to use the Computer Vision service to identify the location of individual items in an image. Which of the following features should you retrieve?

Answer: Objects

4) You want to use the Computer Vision service to analyze images of locations and identify well-known buildings? What should you do?

Answer: Retrieve the categories for the image, specifying the landmarks domain

5) You want to use the Text Analytics service to determine the key talking points in a text document. Which feature of the service should you use?

Answer: Key phrase extraction

6) You want to create a model to predict sales of ice cream based on historic data that includes daily ice cream sales totals and weather measurements. Which Azure service should you use?

Answer: Azure Machine Learning

7) You want to train a model that classifies images of dogs and cats based on a collection of your own digital photographs. Which Azure service should you use?

Answer: Custom Vision

8) You are designing an AI application that uses computer vision to detect cracks in car windshields, and warns drivers when a windshield should be repaired or replaced. When tested in good lighting conditions, the application successfully detects 99% of dangerously damaged glass. Which of the following statements should you include in the application’s user interface?

Answer: When used in good lighting conditions, this application can be used to identify potentially dangerous cracks and defects in windshields. If you suspect your windshield is damaged, even if the application does not detect any defects, you should have it inspected by a professional.

9) An automobile dealership wants to use historic car sales data to train a machine learning model. The model should predict the price of a pre-owned car based on its make, model, engine size, and mileage. What kind of machine learning model should the dealership use automated machine learning to create?

Answer: Regression

10) A bank wants to use historic loan repayment records to categorize loan applications as low-risk or high-risk based on characteristics like the loan amount, the income of the borrower, and the loan period. What kind of machine learning model should the dealership use automated machine learning to create?

Answer: Classification

11) You use the Text Analytics service to perform sentiment analysis on a document, and a score of 0.99 is returned. What does this score indicate about the document sentiment?

Answer: The document is positive.

12) When might you see NaN returned for a score in Language Detection?

Answer: When the language is ambiguous

13) Your organization has an existing frequently asked questions (FAQ) document. You need to create a QnA Maker knowledge base that includes the questions and answers from the FAQ with the least possible effort. What should you do?

Answer: Import the existing FAQ document into a new knowledge base.

14) You need to deliver a support bot for internal use in your organization. Some users want to be able to submit questions to the bot using Microsoft Teams, others want to use a web chat interface on an internal web site. What should you do?

Answer: Create a knowledge base. Then create a bot for the knowledge base and connect the Web Chat and Microsoft Teams channels for your bot

15) You are creating a training pipeline for a regression model, using a dataset that has multiple numeric columns in which the values are on different scales. You want to transform the numeric columns so that the values are all on a similar scale based relative to the minimum and maximum values in each column. Which module should you add to the pipeline?

Answer: Normalize Data

16) You use Azure Machine Learning designer to create a training pipeline and an inference pipeline for a regression model. Now you plan to deploy the inference pipeline as a real-time service. What kind of compute target should you create to host the service?

Answer: Inference Cluster

17) You are using Azure Machine Learning designer to create a training pipeline for a binary classification model. You have added a dataset containing features and labels, a Two-Class Decision Forest module, and a Train Model module. You plan to use Score Model and Evaluate Model modules to test the trained model with a subset of the dataset that was not used for training. Which additional kind of module should you add?

Answer: Split Data

18) You use an Azure Machine Learning designer pipeline to train and test a binary classification model. You review the model’s performance metrics in an Evaluate Model module, and note that it has an AUC score of 0.3. What can you conclude about the model?

Answer: The model performs worse than random guessing.

19) You use Azure Machine Learning designer to create a training pipeline for a classification model. What must you do before deploying the model as a service?

Answer: Create an inference pipeline from the training pipeline

20)You are using an Azure Machine Learning designer pipeline to train and test a K-Means clustering model. You want your model to assign items to one of three clusters. Which configuration property of the K-Means Clustering module should you set to accomplish this?

Answer: Set the Number of Centroids to 3

21) You plan to use the Computer Vision service to read text in a large PDF document. Which API should you use?

Answer: The Read API

22)You plan to use the Form Recognizer pre-built receipt model. Which kind of Azure resource should you create

Answer: Form Recognizer

23)You are using the Form Recognizer service to analyze receipts that you have scanned into JPG format images. What is the maximum file size of JPG file you can submit to the pre-built receipt model?

Answer: 20 MB

24) You plan to build an application that uses the Speech service to transcribe audio recordings of phone calls into text, and then submits the transcribed text to the Text Analytics service to extract key phrases. You want to manage access and billing for the application services in a single Azure resource. Which type of Azure resource should you create?

Answer: Cognitive Services

25) You want to use the Speech service to build an application that reads incoming email message subjects aloud. Which API should you use?

Answer: Text-to-Speech

26)You are developing an application that must take English input from a microphone and generate a real-time text-based transcription in Hindi. Which service should you use?

Answer: Speech

27)You need to use the Translator Text service to translate email messages from Spanish into both English and French? What is the most efficient way to accomplish this goal?

Answer: Make a single call to the service; specifying a “from” language of “es”, a “to” language of “en”, and another “to” language of “fr”.

28)You need to provision an Azure resource that will be used to author a new Language Understanding application. What kind of resource should you create?

Answer: Language Understanding

29)You are authoring a Language Understanding application to support an international clock. You want users to be able to ask for the current time in a specified city, for example “What is the time in London?”. What should you do?

Answer: Define a “city” entity and a “GetTime” intent with utterances that indicate the city intent.

30)You have published your Language Understanding application. What information does a client application developer need to get predictions from it?

Answer: The endpoint and key for the application’s prediction resource

31)You use Azure Machine Learning designer to create a training pipeline for a clustering model. Now you want to use the model in an inference pipeline. Which module should you use to infer cluster predictions from the model?

Answer: Assign Data to Clusters

32)You plan to use the Custom Vision service to train an image classification model. You want to create a resource that can only be used for model training, and not for prediction. Which kind of resource should you create in your Azure subscription?

Answer: Custom Vision

33)You train an image classification model that achieves less than satisfactory evaluation metrics. How might you improve it?

Answer: Add more images to the training set.

34)You have published an image classification model. What information must you provide to developers who want to use it?

Answer: The project ID, the model name, and the key and endpoint for the prediction resource

35)Which of the following results does an object detection model typically return for an image?

Answer: A class label, probability, and bounding box for each object in the image

36)You plan to use a set of images to train an object detection model, and then publish the model as a predictive service. You want to use a single Azure resource with the same key and endpoint for training and prediction. What kind of Azure resource should you create?

Answer: Cognitive Services

37)You plan to use Face to detect human faces in an image. How does the service indicate the location of the faces it detects?

Answer: A set of coordinates for each face, defining a rectangular bounding box around the face

38)What is one aspect that may impair facial detection?

Answer: Extreme angles

39) You want to use Face to identify named individuals. What must you do?

Answer: Use Face to create a group containing multiple images of each named individual, and train a model based on the group

40)You want to extract text from images and then use the Text Analytics service to analyze the text. You want developers to require only one key and endpoint to access all of your services. What kind of resource should you create in your Azure subscription?

Answer: Cognitive Services

41 ) Anomaly detector is stateful

Answer: False

42) We are designing an AI solution to monitor meetings and want to know when facial expressions indicate people being angry or scared. Which cognitive service should we use?

Answer: Face API

43) You train an image classification model that achieves less than satisfactory evaluation metrics? How might you improve it?

Answer: Add more images to the training set

44) You open gallery section in your mobile phone and see that thumbnails are generated for images. This is a capability of-

Answer: Computer Vision

45 ) __ can be used for medical imaging diagnosis

Answer: Image Classification

46) Having AI developers working within a framework of governance and organizational principles that ensure the solution meets ethical and legal standards, is an example of which Microsoft responsible AI principle?

Answer: Accountability

47) The technique to iteratively test a trained model with data it wasn’t trained with and compare the predicted value with the actual known value is known as __

Answer: Residuals

48) The free tier edition of Read API allows for _ pages, versus __ for the paid version

Answer: 2,2000

49) Which feature of Azure provides the capability to deploy an AI solution without having to code?

Answer: Azure Machine learning designer

50) Which Azure service should you use to determine if a portrait of a person is in color or black-and-white?

Answer: Computer Vision

51) You are developing an application for tourists to use as a text-based or audio-based translator. Which Azure services can help?

Answer: Azure speech

52) You wish to upload your custom images for an image classification machine learning service you are creating. What options are available to you?

Answer: Custom Vision Portal

53) Which Azure service supports both real-time and batch-based processing?

Answer: Speech to text

54) Which of the following tasks would be a good fit for the Speech-to-Text?

Answer: Real time voice-char transcription from a microphone

55) Which Azure services are used for LUIS?

Answer: Language Understanding

56) Azure Custom Vision portal is accessed through _

Answer: https://customvision.ai

57) An automobile dealership wants to use historic car sales data to train a machine learning model. The model should predict the price of a pre-owned car based on characteristics like its age, engine size, and mileage. What kind of machine learning model does the dealership need to create?

Answer: Regression

58) You are configuring a LUIS service. Identify the entity(s) in the following voice command: “Computer, switch on the lights in the living room”

Answer: Living Room

59) Which module should you use to provide a simple metric to compare the performance of multiple training models?

Answer: Evaluate Model

60) Which key steps form part of the Authoring phase of LUIS?

Answer: Creating Entities

61) Which Azure service helps you develop a chat bot to take the load off your call center staff?

Answer: QnA Maker with Bot Service

62) Which Azure service is best for detecting popular brand logos?

Answer: Computer Vision

63) If you create a Cognitive Services resource, client applications need different keys and endpoint for different service they use

Answer: True

64) OCR API works best asynchronously

Answer: True

65) A model is developed to take medical images as input and decide on whether tumor is benign or malignant. This is an example of-

Answer: Classification

66) You wish to develop an application for tourists which they can use as a text or audio-based translator. Azure services that can help are-

Answer: Azure Speech

67) Which type of datastores are created by Azure machine learning studio?

Answer: Azure Blog Storage

68) Read API returns a hierarchy of information including _

Answer: Pages

69) Classification machine learning models use a set of inputs known as-

Answer: Features

70) How does the translation engine know when an utterance has finished?

Answer: After a pause in the audio

71) Which service is used to suggest class and bounding boxes you add to training set after an initial dataset:

Answer: tag smart

72) Classification is an example of __ machine learning

Answer: Supervised

73) You are capturing images in which texts are dominant. You are using an API which is now returning false positives. Which API are you currently using?

Answer: OCR API

74) Your organization has an existing frequently asked questions (FAQ) document. You need to create a QnA Maker knowledge base that includes the questions and answers from the FAQ with the least possible effort. What should you do?

Answer: Import the existing FAQ document into a new knowledge base.

75) You wish to develop an application which can read street signs. Which azure service do you deploy?

Answer: Azure Computer Vision

76) Paid subscription version of the Form Recognizer supports up to _ pages and a maximum of _ lines per page.

Answer: 400 Pages

77) Microsoft’s responsible AI principles include…?

Answer: Fairness

78) Image classification can be used for the following use cases

Answer: Object Detection

79) What is the typical minimum number of Compute Cluster nodes recommended for training in a Production environment?

Answer: 2

80) You need to ensure your AI-based application users are aware of the limitations of your app. This is an example of which Microsoft responsible AI principle?

Answer: Transperancy

81) Deploying an Al service that monitors people of certain ethnicity for closer inspection in a retail store Is a violation of Microsoft responsible Al principle?

Answer: Inclusiveness

82) The residual histogram for a highly accurate machine learning model will have most frequently occurring residual values close to

Answer: O at the center of residual axis

83) If you consider the concept of ‘Describing an Image’ of Computer Vision, which of the following are correct:

Answer: The phrases will be arranged in descending order of their confidence score

84) The information that we need to use to access Computer Vision service-

Answer: Key or Endpoint

85) We are designing an Al solution to monitor meetings and want to know when facial expressions indicate people being angry or scared. Which cognitive service should we use?

Answer: Face API

86) The OCR API in Azure Computer Vision service Is used to scan newspapers and magazines

Answer: TRUE

87) The ability of a software agent to participate in a conversation is known as

Answer: Conversional Al

88) Which Azure service would you deploy to detect a sudden spike in network traffic?

Answer: Azure Anomaly detector

89) You have used a wrong language code in Text Analytics. What sentiment analysis score should you expect?

Answer: 0

90) How do you access the QnAmaker portal?

Answer: qnamaker.ai

91) If you consider the concept of ‘Describing an Image’ of Computer Vision, which of the following are correct:

Answer: descending order

92)You are developing an application for the visually impaired. Your application will read text books out loud. Which Azure services can you use?

Answer: Speech

93) What is the easiest method to define elements of your LUIS model?

Answer: LUIS Portal

94) Read API works best synchronously

Answer: False

95)OCR API works best synchronously

Answer: True

96)Computer vision is the best Azure resource for detecting, analyzing and working with Faces

Answer: False

97)The ability to automatically detect sudden spike in a time-series based data is known as….?

Answer: Anomaly Detection

98)The OCR API returns a hierarchy of information including _

Answer: Pages

99)You wish to separate your training and prediction resources for classifying your own images. Which service works best?

Answer: Custom Vision

100)What is the best way to access Azure Machine Learning studio?

Answer: ml.azure.com

Leave a Comment