DRAG DROP -
Match the facial recognition tasks to the appropriate questions.
To answer, drag the appropriate task from the column on the left to its question on the right. Each task may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
Select and Place:
Show Answer
Correct Answer: Do two images of a face belong to the same person?
verification
Does this person look like other people?
similarity
Who is this person in this group of people?
identification
Explanation: Verification checks whether two faces are from the same person (1:1). Similarity finds faces that look alike without confirming identity. Identification determines who a person is by matching one face against a group (1:N).
Question 108
Which statement is an example of a Microsoft responsible AI principle?
A. AI systems must use only publicly available data
B. AI systems must be transparent and inclusive
C. AI systems must keep personal details public
D. AI systems must protect the interests of the company
Show Answer
Correct Answer: B
Explanation: Microsoft’s Responsible AI principles include transparency, fairness, inclusiveness, reliability and safety, privacy and security, and accountability. Option B directly reflects these principles, whereas the other options contradict responsible AI practices.
Question 109
Which two scenarios are examples of a natural language processing workload? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A. monitoring the temperature of machinery to turn on a fan when the temperature reaches a specific threshold
B. a smart device in the home that responds to questions such as, "What will the weather be like today?"
C. a website that uses a knowledge base to interactively respond to users' questions
D. assembly line machinery that autonomously inserts headlamps into cars
Show Answer
Correct Answer: B, C
Explanation: Natural language processing involves understanding and generating human language. A smart home device that answers spoken questions (B) and a website that interactively responds to users’ questions using a knowledge base (C) both require interpreting natural language input and producing language-based responses. The other options involve sensor monitoring or mechanical automation, not language processing.
Question 110
You have an Azure Machine Learning pipeline that contains a Split Data module.
The Split Data module outputs to a Train Model module and a Score Model module.
What is the function of the Split Data module?
A. scaling numeric variables so that they are within a consistent numeric range
B. creating training and validation datasets
C. diverting records that have missing data
D. selecting columns that must be included in the model
Show Answer
Correct Answer: B
Explanation: In Azure Machine Learning, the Split Data module is used to divide an input dataset into separate subsets, typically one for training a model and one for testing/validation or scoring. In a pipeline where its outputs feed a Train Model and a Score Model module, its function is to create training and validation (or testing) datasets. The other options describe different preprocessing modules (scaling, handling missing data, or selecting columns).
Question 111
You need to build an app that will read recipe instructions aloud to support users who have reduced vision.
Which version service should you use?
A. Language service
B. Translator
C. Speech
D. Personalizer
Show Answer
Correct Answer: C
Explanation: The requirement is to read recipe instructions aloud, which means converting text into spoken audio. This is provided by the Speech service (Text-to-Speech). The Language service analyzes text, Translator translates text between languages, and Personalizer is for recommendations, not audio output.
Question 112
You have an AI solution that provides users with the ability to control smart devices by using verbal commands.
Which two types of natural language processing (NLP) workloads does the solution use? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
A. text-to-speech
B. key phrase extraction
C. speech-to-text
D. language modeling
E. translation
Show Answer
Correct Answer: C, D
Explanation: A verbal smart‑device control solution must first convert spoken commands into text, which is done using speech‑to‑text. After transcription, the system needs to understand the intent and meaning of the command (for example, identifying the requested action and device), which is handled by language modeling. Other options like key phrase extraction or translation are not sufficient for full intent understanding, and text‑to‑speech is optional rather than required by the question.
Question 113
DRAG DROP -
Match the types of natural language processing workloads to the appropriate scenarios.
To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once, more than once, or not at all.
NOTE: Each correct match is worth one point.
Select and Place:
Show Answer
Correct Answer: Entity recognition → Extracts persons, locations, and organizations from the text.
Sentiment analysis → Evaluates text along a positive–negative scale.
Translation → Converts text to a different language.
Explanation: Entity recognition identifies named entities, sentiment analysis measures opinion polarity, and translation changes text from one language to another.
Question 114
HOTSPOT -
Select the answer that correctly completes the sentence.
Hot Area:
Show Answer
Correct Answer: computer vision.
Explanation: Counting animals from a video feed requires detecting and analyzing objects within images or video frames, which is a core task of computer vision.
Question 116
You send an image to a Computer Vision API and receive back the annotated image shown in the exhibit.
Which type of computer vision was used?
A. object detection
B. face detection
C. optical character recognition (OCR)
D. image classification
Show Answer
Correct Answer: A
Explanation: The annotated image shows individual objects identified with bounding boxes and labels. Returning object classes along with their locations is characteristic of object detection. Image classification would label the whole image only, face detection is limited to faces, and OCR is for extracting text.
Question 118
Which two languages can you use to write custom code for Azure Machine Learning designer? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A. Python
B. R
C. C#
D. Scala
Show Answer
Correct Answer: A, B
Explanation: Azure Machine Learning designer supports custom code through built-in modules that execute Python scripts and R scripts. C# and Scala are not supported for custom code within the designer environment.
$19
Get all 230 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.
