You have an AI-based loan approval system.
During testing, you discover that the system has a gender bias.
Which responsible Al principle does this violate?
A. accountability
B. reliability and safety
C. transparency
D. fairness
Show Answer
Correct Answer: D
Explanation: A gender bias in a loan approval system means that individuals are treated unequally based on a protected attribute. This directly violates the responsible AI principle of fairness, which requires AI systems to provide equitable and non-discriminatory outcomes.
Question 55
Which machine learning technique can be used for anomaly detection?
A. A machine learning technique that classifies objects based on user supplied images.
B. A machine learning technique that understands written and spoken language.
C. A machine learning technique that classifies images based on their contents.
D. A machine learning technique that analyzes data over time and identifies unusual changes.
Show Answer
Correct Answer: D
Explanation: Anomaly detection focuses on identifying unusual or unexpected patterns or changes in data, often over time. Techniques that analyze temporal data to detect deviations from normal behavior are specifically designed for anomaly detection, making option D correct.
Question 56
HOTSPOT
-
Select the answer that correctly completes the sentence.
Show Answer
Correct Answer: a reliability and safety
Explanation: Withholding predictions when required inputs are missing or anomalous prevents unsafe or incorrect outcomes, which aligns with ensuring systems operate reliably and safely.
Question 57
HOTSPOT
-
Select the answer that correctly completes the sentence.
Show Answer
Correct Answer: Regression
Explanation: The sale price is a continuous numeric value, which is predicted using regression models rather than classification or clustering.
Question 58
You need to identify groups of rows with similar numeric values in a dataset.
Which type of machine learning should you use?
A. clustering
B. regression
C. classification
Show Answer
Correct Answer: A
Explanation: The task is to find groups of rows with similar numeric values without predefined labels. This is an unsupervised learning problem, and clustering is specifically designed to group similar data points. Regression predicts numeric outcomes, and classification assigns predefined labels, neither of which fits this goal.
Question 59
DRAG DROP
-
Match the types of AI 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 selection is worth one point.
Show Answer
Correct Answer: Identify handwritten letters.
Computer vision
Predict the sentiment of a social media post.
Natural language processing
Identify an unusual credit card payment.
Anomaly detection
Group animals based on multiple measurements.
Machine Learning (Clustering)
Explanation: Handwritten text recognition is a vision task; sentiment analysis processes text; detecting unusual payments focuses on outliers; grouping by measurements without labels is clustering.
Question 60
You use Azure Machine Learning designer to build a model pipeline.
What should you create before you can run the pipeline?
A. a registered model
B. a compute resource
C. a Jupyter notebook
Show Answer
Correct Answer: B
Explanation: In Azure Machine Learning designer, a pipeline cannot run without a compute resource (compute target). The compute resource provides the CPU/GPU and memory required to execute pipeline modules such as data preparation and model training. A registered model is only created after training, and a Jupyter notebook is optional and not required to run designer pipelines.
Question 61
HOTSPOT -
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Hot Area:
Show Answer
Correct Answer: Yes
No
Yes
Explanation: Language Detection is a core feature of Azure Cognitive Service for Language. Handwritten signature detection is not handled by the Language service; it belongs to vision/ink recognition capabilities. Named Entity Recognition in the Language service can identify organizations and companies mentioned in text.
Question 62
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. entity recognition
D. key phrase extraction
Show Answer
Correct Answer: D
Explanation: Identifying the main talking points in a collection of documents involves extracting the most important concepts and topics discussed. Key phrase extraction is designed specifically to pull out these representative phrases, whereas language detection identifies language, sentiment analysis measures opinion, and entity recognition finds named entities.
Question 63
HOTSPOT
-
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Yes
No
Yes
Explanation: Chatbots can accept voice input through speech-to-text. A single chatbot can be deployed across multiple channels. Conversation flows commonly combine natural language understanding with constrained options like buttons or menus.
$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.
