1.

What feature involves extracting key insights from both structured and unstructured
data sources?
A. OCR
B. Image classification
C. Object detection
D. Knowledge mining

2. Which machine learning approach is suitable for discerning whether a social media post
expresses positive or negative sentiment?
A. Classification
B. Clustering
C. Regression

3. Match the appropriate Azure AI vision service to the below scenario.

Statement:
Confirm that a driver is looking at the road whilst driving a vehicle.
A. Face detection
B. Image classification
C. Object detection
D. Optical character recognition

4. Match the appropriate Azure AI vision service to the below scenario.

Statement:
Identify dog’s breed from a picture.
A. Face detection
B. Object detection
C. Image classification
D. Optical character recognition

5. Match the appropriate Azure AI vision service to the below scenario.

Statement:
Find pedestrians on a traffic light camera's video stream.
A. Object detection
B. Face detection
C. Image classification
D. Optical character recognition
6. What is a prominent characteristic of generative AI models?
A. The generation of new original content based on natural language input
B. The translation of text from one language to another
C. Its use in tasks involving spatial analysis
D. The conducting of regression analysis

7. Which scenario exemplifies a common application of Generative AI?

A. A system that classifies emails as spam or not spam
B. A model that clusters customers into different segments based on their behavior
C. A tool that detects anomalies in network traffic
D. A chatbot that can generate creative content based on the input it receives from
users

8. What is a machine learning method that predicts or determines the category, type, or
class of a data item?
A. Fairness
B. Object detection
C. Classification

9. To complete the statement , select the appropriate option in the answer area.
Statement:
Which model can be utilized to forecast the sale price of auctioned items.
A. Classification
B. Regression
C. Clustering

10. How can you assess the performance of a classification model?

A. Mean absolute error (MAE)
B. True positive rate
C. Coefficient of determination (R2)
D. Coefficient of determination (R2)

11. Which two components are draggable onto a canvas within Azure Machine Learning
designer?
 A. Dataset
B. Compute
C. Module
D. Pipeline

12. To complete the sentence, choose the appropriate option in the answer area.
____________________is the calculated probability of a correct image classification.
A. Accuracy
B. Root Mean Square Error
C. Confidence

13. To complete the sentence, choose the appropriate option in the answer area.
Is ensuring that an AI system does not provide a prediction when important fields
contain unusual or missing values a principle for responsible AI?
A. An inclusiveness
B. A privacy and security
C. A transparency
D. A reliability and safety

14. To complete the sentence, choose the appropriate option in the answer area.
Is ensuring that the numeric variables in training data are on a similar scale an example
of what?
A. Feature engineering
B. Data ingestion
C. Feature selection
D. Model training

15. To complete the sentence, choose the appropriate option in the answer area. Is
assigning classes to images before training a classification model an example of what?
A. Evaluation
B. Feature engineering
C. Labeling
D. Hyperparameter tuning

16. You have an Azure Machine Learning model that predicts product quality. The model has
a training dataset that contains 50,000 records. A sample of the data is shown in the
following table.
 For each of the following statements select Yes if the statement is true. Otherwise, select
No.
Statements:
a. Mass (kg) is a feature.
b. Quality test is label.
c. Temperature (C) is a label.

A. Yes, No, Yes

B. No, No Yes
C. Yes, Yes, No

17. "Which two actions are performed during the data ingestion and data preparation stage
of an Azure Machine Learning process?"
A. Calculate the accuracy of the model.
B. Combine multiple datasets.
C. Score test data by using the model.
D. Remove records that have missing values.

18. What Azure Machine Learning type would you use to forecast the animal population of
an area?
A. Clustering
B. Regression
C. Classification

19. Which two programming languages are compatible for coding custom solutions within
Azure Machine Learning designer?
A. Python
B. C#
C. R
D. Scala
20. For each of the following statements. Choosing yes if the statements is true. Otherwise,
choosing no.
Statements:
a. For a regression mode, labels must be numeric.
b. For a clustering model, labels must be used.
c. For a classification model, labels must be numeric.

A. Yes, No, Yes

B. No, Yes, Yes
C. Yes, No, No

21. What type of AI workload should your company utilize to develop a recycling machine
that automatically identifies bottles of the correct shape and rejects all other items?
A. Anomaly detection
B. Computer vision
C. Conversational al
D. Natural language processing

22. For each of the following statements. Choosing yes if the statements is true. Otherwise,
choosing no.
Statements:
a. When creating an object detection model in the Custom Vision service, you must
choose a classification type of either Multilabel or Multiclass.
b. You can create an object detection model in the Custom Vision service to find the
location of content within an image.
c. When creating an object detection model in the Custom Vision service, you can select
from a set of predefined domains.

A. Yes, No, Yes

B. No, Yes, Yes
C. Yes. No, No

23. What are two scenarios where you can apply the Form Recognizer service?
A. Extract the invoice number from an invoice.
B. Translate a form from French to English.
C. Identify the retailer from a receipt.
D. Find image of product in a catalog.
24. To complete the sentence, choose the appropriate option in the answer area.
Counting the number of animals in an area based on a video feed is an example
of_____________?
A. Forecasting
B. Conversational AI
C. Computer vision
D. Anomaly detection

25. To the following statement ,select "Yes" if the statement is true and "No" if it's false for
the given scenario: You have a database containing employee information along with
their respective photos, and you are assigning tags to new employee photos.
statements
a. Face service can be used to perform facial recognition for employees.
b. The pay service will be more accurate if you provide more sample photos of each
employee from different angles.
c. If an employee is wearing sunglasses, the face service will always feel to recognize the
employee

A. Yes ,No ,Yes

B. No ,Yes ,Yes
C. Yes ,Yes ,No
26. What need can be addressed by utilizing sentiment analysis?
A. Extract brand information from documents.
B. Transcribe the recording of a marketing presentation into text.
C. Analyze social media for a brand.
D. Find the use of brand names in documents.

27. Which two types of data inputs can natural language processing (NLP) workloads
handle?
A. A static BMP file
B. An audio stream
C. A static PNG file
D. A text document

28. Which two scenarios are governed by the accountability principle in responsible AI?
A. Keeping personal details private
B. Meeting ethical standards
C. Treating people fairly
 D. Following a governance framework

29. Which responsible AI principle focuses on reducing bias in a machine learning model?
A. Accountability
B. Inclusiveness
C. Fairness
D. Transparency

30. Which responsible AI principle mandates rigorous testing of an AI-based application to

mitigate potential risks to human life?
A. Accountability
B. Fairness
C. Inclusiveness
D. Reliability & safety

31. Which scenario exemplifies a knowledge mining workload?

A. Identifying spoken languages in published multilingual audio files
B. Gaining insight into potential liabilities from an unstructured set of contract
documents
C. Identifying commercial brands on published video files
D. Enabling voice assistant capability in a travel booking app

32. Which two guiding principles are included in Microsoft's approach to responsible AI?
A. Simplified Identity Governance
B. Inclusiveness
C. Reliability & Safety
D. Secure Adaptive Access

33. Identify an instance of a computer vision task?

A. Translating text in real time from Korean to English
B. Identifying unexpected anomalies in a credit card transactions log
C. Transcribing speech in real time in a call center telephony
D. Classifying crops on the images taken by a drone's camera

34. For each of the following statements. Choosing yes if the statement is true. Otherwise,
choosing no.
Statements:
a. Computer vision can be used to transcribe video conference calls.
b. Computer vision can be used to extract printed text from photos.
c. Computer vision can be used to detect the presence of people on a security cameras
video stream.
 A. Yes ,No ,Yes
B. No ,Yes ,Yes
C. Yes ,Yes ,No

35. For each of the following statements. Choosing yes if the statement is true. Otherwise,
choosing no.
Statements:
a. Key phrase extraction performs better on smaller amounts of text.
b. Sentiment analysis performs better on smaller amounts of text.
c. Speech Synthesis Markup Language (SSML) is based on JSON format.

A. Yes ,No ,Yes

B. No ,Yes ,No
C. Yes ,Yes ,No

36. Which responsible AI principle does the HR AI system follow by screening job candidates
without considering personal factors like age, gender, ethnicity, or physical abilities?
A. Transparency
B. Fairness
C. Inclusiveness
D. Accountability

37. Which responsible AI principle focuses on ensuring that you are fully informed about the
limitations of AI-based systems?
A. Accountability
B. Fairness
C. Inclusiveness
D. Transparency

38. For each of the following statements. Choosing yes if the statement is true. Otherwise,
choosing no.
Statements:
a. According to the principle of fairness, Al solutions should treat all people equally.
b. According to the principle of inclusiveness, Al solutions should empower everyone
and engage people.
c. According to the principle of accountability, Al solutions should be liable for their
actions.

A. Yes ,No ,Yes

B. No ,No ,Yes
 C. Yes ,Yes ,No

39. For each of the following statements. Choosing yes if the statement is true. Otherwise,
choosing no.
Statements:
a. Inclusiveness indicates that Al systems should bring the benefits of an Al- based
solution to all members of society.
b. Inclusiveness makes users aware of the purpose and limitations of an Al- based
solution.
c. Inclusiveness is an Al-based solution that has the potential to empower and engage all
communities in the world.

A. Yes ,No ,Yes

B. No ,No ,Yes
C. Yes ,Yes ,No

40. Which situation uses computer vision?

A. Detecting abnormalities in health scans.
B. Translating commands into actions.
C. Discovering financial system fraud.
D. Finding relevant information to answer a specific customer question.

41. What type of Natural Language Processing (NLP) workload is demonstrated when an AI
solution analyzes customer feedback and categorizes it as positive, neutral, or negative?
A. Speech synthesis
B. Named entity recognition
C. Sentiment analysis
D. Speech translation

42. Match the responsible Al principles to the objective.

Statement:
Protect personal information.
A. Fairness
B. Privacy & security
C. Accountability
D. Transparency

43. Match the responsible Al principles to the objective.

Statement:
Quantify risk and harm to life.
A. Fairness
 B. Privacy & security
C. Reliability & safety
D. Transparency

44. Match the responsible Al principles to the objective.

Statement:
Gain trust from users.
A. Fairness
B. Transparency
C. Privacy & security
D. Reliability & safety

45. Which responsible AI principle is exemplified by a company conducting thorough testing

and deployment management of the AI system that drives a driverless taxi solution?
A. Accountability
B. Reliability and safety
C. Transparency
D. Inclusiveness

46. What technology enables interactions between computers and humans using text and
speech?
A. Natural Language Processing (NLP)
B. Computer Vision
C. Machine Learning
D. Augmented Reality

47. Match the responsible Al principles to the objective ,To below.

Statement:
Applications that interpret visual input from images.
A. Forecasting
B. Computer vision
C. Natural language processing
D. Conversational AI

48. Match the responsible Al principles to the objective.

Statement:
Applications that interpret written text

A. Forecasting
B. Computer vision
C. Natural language processing.
 D. Conversational AI

49. What type of natural language processing solution is demonstrated by incorporating

synthesized neural voice into your robotic system?
A. Key phrase extraction
B. Sentiment analysis
C. Speech to text
D. Text to speech

50. Which of the following options best describes a machine learning method used for
grouping data points that share similar traits?
A. Clustering
B. Regression
C. Classification
D. Dimensionality reduction

51. In which two situations can you utilize the Azure AI Document Intelligence service?
A. Translate a form from French to English.
B. Extract the invoice number from an invoice.
C. Identify the retailer from a receipt.
D. Find the image of the product in a catalogue.

52. What type of AI workload should the company opt for if they aim to develop a recycling
machine capable of automatically recognizing bottles based on their shape and rejecting
other items?
A. Anomaly detection
B. Conversational AI
C. Natural language processing
D. Computer vision

53. How can you recognize an example of a generative AI workload from the following
scenarios?
A. Predicting stock prices based on historical data
B. Generating an original new image based on its description
C. Classifying images into different categories
D. Recommending products to customers based on their past purchases.

54. Which ethical AI principle does the company demonstrate by providing clear
explanations of how its banking AI system operates and the factors it considers when
approving mortgage applications?
A. Inclusiveness
 B. Fairness
C. Transparency
D. Transparency

55. Which two situations exemplify document intelligence workloads?

A. Extraction of contact details from scanned business cards
B. Translation of a document from one language into another
C. Classification of provided contract files
D. Generation of Python code for provided functionality description.

56. What is an example of assessing vehicle damage from a photograph?

A. Image classification
B. Natural language processing
C. Anomalies detection
D. Sentiment Analysis

57. You are developing a chatbot solution in Azure.

Which service should you use to determine a user’s intent?
A. Translator
B. Language
C. Azure Cognitive Search
D. Speech

58. You have a bot that identifies the brand names of products in images of supermarket
shelves
A. AI enrichment for Azure Search capabilities
B. Computer Vision Image Analysis capabilities
C. Custom Vision Image Classification capabilities
D. Language Understanding capabilities

59. As You need to identify street names based on street signs in photographs.
Which type of computer vision should you use?
A. Object detection
B. Optical character recognition (OCR)
C. Image classification
D. Facial recognition

60. You are building a tool that will process images from retail stores and identify the
products of competitors. The solution must be trained on images provided by your
company. Which Azure AI service should you use?
A. Azure AI Document intelligence
 B. Custom vision
C. Face
D. Computer vision

61. Complete the following sentence :

Detecting unusual temperature fluctuations for a large machine is an example of
________ ?
A. Computer vision workload
B. Anomaly detection workload
C. Knowledge mining workload

62. A smart device responds to questions such as "When is my next appointment" is an

example of conversational AI ?
A. Yes
B. No

63. You are building a Language Understanding model for an e-commerce business. You
need to ensure that the model detects when utterances are outside the intended scope
of the model. What should you do?
A. Export the model
B. Add utterances to the None intent
C. Create a prebuilt task entity
D. Create a new model

64. You have 100 instructional videos that do NOT contain any audio. Each instructional
video has a script. You need to generate a narration audio file for each video based on
the script. Which type of workload should you use?
A. Language modeling
B. Speech recognition
C. Speech synthesis
D. Translation

65. You need to convert receipts into transactions in a spreadsheet. The spreadsheet must
include the date of the transaction, the merchant, the total spent, and any taxes paid.
Which Azure AI service should you use?
A. Custom Vision
B. Azure AI Document Intelligence
C. Language

66. Which type of natural language processing (NLP) entity is used to identify a phone
number?
 A. regular expression
B. machine-learned
C. list
D. Pattern.any

67. You are developing a solution that uses the Language service. You need to identify the
main talking points in a collection of documents. Which type of natural language
processing should you use?
A. Language detection
B. sentiment analysis
C. key phrase extraction

68. You have a solution that analyzes social media posts to extract the mentions of city
names and the city names discussed most frequently. Which type of natural language
processing (NLP) workload does the solution use?
A. Speech recognition
B. Sentiment analysis
C. Key phrase extraction
D. Entity recognition

69. Drag and Drop

A. 1,5,3,2
B. 1,3,2,4
 C. 5,2,1,4

70. In a machine learning model, the data that is used as inputs are called ________.
A. Labels
B. Variables

71. You have a natural language processing (NLP) model that was created by using data
obtained without permission. Which Microsoft principle for responsible AI does this
breach?
A. reliability and safety
B. privacy and security
C. inclusiveness

72. How can we mitigate harmful content generation in Azure OPEN AI service ?
A. DALL-E Model
B. Codex
C. Content filters

73. Ensuring an AI system does not provide a prediction when important fields contain
unusual or missing values is _____________ principle for responsible AI.
A. an inclusiveness
B. a privacy and safety
C. a reliability and safety
D. a transparency

74. Choose the correct answer(s) below?

A. 1,2,3
B. 3,2,1
C. 1,3,2
 D. 2,3,1

75. What are two metrics that you can use to evaluate a regression model? Each correct
answer presents a complete solution.
A. coefficient of determination (R2)
B. F1 score
C. root mean squared error (RMSE)
D. area under curve (AUC)
E. balanced accuracy

76. Assigning classes to images before training a classification model is an example of

_____ ?
A. Labeling
B. Evaluation
C. feature engineering

77. For the below statement, select Yes if the statement is true. Otherwise, select No.
Statement : For a regression model, labels must be numeric.
A. Yes
B. No

78. For the below statement, select Yes if the statement is true. Otherwise, select No.
Statement : For a classification model, labels must be numeric.
A. Yes
B. No

79. For the below statement, select Yes if the statement is true. Otherwise, select No.
Statement : You can use the Translator service to detect the language of a given text.
A. Yes
B. No

80. Ability to extract subtotal and total from a receipt is capability of _____ service.
A. Custom Vision
B. Document Intelligence
C. Text Analytics

81. Which Azure service will you be using for to analyze the text for the presence of profane
language.
A. Azure AI Computer vision
B. Azure AI content safety
C. Azure AI custom vision
82. You need to extract text from the images. Which Azure service will you be using for this ?
A. Azure AI Language
B. Azure AI vision
C. Azure AI Document Intelligence

83. You created a Custom Vision model. You want your model to detect trained objects on
the photos. What information will you get about each object if you are using an object
detection model?
A. Image type
B. Bounding box
C. Image category
D. Class name
E. Probability score
F. Content name