Skip to content

Latest commit

 

History

History
1481 lines (1003 loc) · 47.4 KB

ai-900.md

File metadata and controls

1481 lines (1003 loc) · 47.4 KB
Raw

Question 1:

Which three sources can be used to generate questions and answers for a knowledge base? Each correct answer presents a complete solution.

Select all answers that apply.

  • A webpage
  • An audio file
  • An existing FAQ document
  • An image file
  • Manually entered data

Correct Answer: A webpage, An existing FAQ document, Manually entered data

Short Explanation: A webpage and existing FAQ documents provide pre-structured information, while manually entered data allows for custom input into the knowledge base.

Question 2:

Select the answer that correctly completes the sentence.

____ use plugins to provide end users with the ability to get help with common tasks from a generative AI model.

Select only one answer.

  • Copilots
  • Language Understanding solutions
  • Question answering models
  • RESTful API services

Correct Answer: Copilots

Short Explanation: Copilots utilize plugins to assist users with tasks using AI models, enhancing productivity and task management.

Question 3:

At which layer can you apply content filters to suppress prompts and responses for a responsible generative AI solution?

Select only one answer.

  • Metaprompt and grounding
  • Model
  • Safety system
  • User experience

Correct Answer: Safety system

Short Explanation: Content filters are part of the safety system layer, designed to manage and restrict harmful or inappropriate content.

Question 4:

Select the answer that correctly completes the sentence.

____ can return responses, such as natural language, images, or code, based on natural language input.

Select only one answer.

  • Computer vision
  • Deep learning
  • Generative AI
  • Machine learning
  • Reinforcement learning

Correct Answer: Generative AI

Short Explanation: Generative AI models are capable of producing diverse outputs like text, images, and code from natural language inputs.

Question 5:

Select the answer that correctly completes the sentence.

____ can be used to identify constraints and styles for the responses of a generative AI model.

Select only one answer.

  • Data grounding
  • Embeddings
  • System messages
  • Tokenization

Correct Answer: System messages

Short Explanation: System messages define the behavior, style, and constraints for responses generated by AI models.

Question 6:

Which two capabilities are examples of a GPT model? Each correct answer presents a complete solution.

Select all answers that apply.

  • Create natural language.
  • Detect specific dialects of a language.
  • Generate closed captions in real-time from a video.
  • Synthesize speech.
  • Understand natural language.

Correct Answer: Create natural language, Understand natural language

Short Explanation: GPT models are primarily designed for generating and understanding natural language.

Question 7:

Which three capabilities are examples of image generation features for a generative AI model? Each correct answer presents a complete solution.

Select all answers that apply.

  • Animation of static images
  • Creating variations of an image
  • Editing an image
  • Extracting RGB values from an image
  • New image creation

Correct Answer: Creating variations of an image, Editing an image, New image creation

Short Explanation: Generative AI models can create new images, modify existing ones, and produce variations, expanding creative possibilities.

Question 8:

You plan to develop an image processing solution that will use DALL-E as a generative AI model.

Which capability is NOT supported by the DALL-E model?

Select only one answer.

  • Image description
  • Image editing
  • Image generation
  • Image variations

Correct Answer: Image description

Short Explanation: DALL-E specializes in generating and editing images and creating variations, but does not describe images.

Question 9:

Select the answer that correctly completes the sentence.

____ can search, classify, and compare sources of text for similarity.

Select only one answer.

  • Data grounding
  • Embeddings
  • Machine learning
  • System messages

Correct Answer: Embeddings

Short Explanation: Embeddings are representations that enable comparison and classification of textual data based on similarity.

Question 10:

Which artificial intelligence (AI) technique serves as the foundation for modern image classification solutions?

Select only one answer.

  • Semantic segmentation
  • Deep learning
  • Linear regression
  • Multiple linear regression

Correct Answer: Deep learning

Short Explanation: Deep learning, particularly through convolutional neural networks, underpins contemporary image classification technologies.

Question 11:

Which artificial intelligence (AI) technique should be used to extract the name of a store from a photograph displaying the store front?

Select only one answer.

  • Image classification
  • Natural language processing (NLP)
  • Optical character recognition (OCR)
  • Semantic segmentation

Correct Answer: Optical character recognition (OCR)

Short Explanation: OCR is used to extract and recognize text from images, such as store names on storefronts.

Question 12:

Which computer vision solution provides the ability to identify a person's age based on a photograph?

Select only one answer.

  • Facial detection
  • Image classification
  • Object detection
  • Semantic segmentation

Correct Answer: Facial detection

Short Explanation: Facial detection technology can analyze facial features to estimate a person’s age from photographs.

Question 13:

Which computer vision service provides bounding coordinates as part of its output?

Select only one answer.

  • Image analysis
  • Image classification
  • Object detection
  • Semantic segmentation

Correct Answer: Object detection

Short Explanation: Object detection identifies objects within images and provides bounding box coordinates for their locations.

Question 14:

Which process allows you to use optical character recognition (OCR)?

Select only one answer.

  • Digitizing medical records
  • Identifying access control for a laptop
  • Identifying wildlife in an image
  • Translating speech to text

Correct Answer: Digitizing medical records

Short Explanation: OCR converts printed or handwritten text into digital form, useful for digitizing documents like medical records.

Question 15:

What allows you to identify different types of bone fractures in X-ray images?

Select only one answer.

  • Conversational artificial intelligence (AI)
  • Facial detection
  • Image classification
  • Object detection

Correct Answer: Image classification

Short Explanation: Image classification can be trained to recognize and differentiate between various types of bone fractures in X-ray images.

Question 16:

What allows you to identify different vehicle types in traffic monitoring images?

Select only one answer.

  • Image classification
  • Linear regression
  • Object detection
  • Optical character recognition (OCR)

Correct Answer: Object detection

Short Explanation: Object detection systems can identify and classify different types of vehicles in traffic images.

Question 17:

Which three parts of the machine learning process does the Azure AI Vision eliminate the need for? Each correct answer presents part of the solution.

Select all answers that apply.

  • Azure resource provisioning
  • Choosing a model
  • Evaluating a model
  • Inferencing
  • Training a model

Correct Answer: Choosing a model, Evaluating a model, Training a model

Short Explanation: Azure AI Vision simplifies the machine learning process by handling model selection, evaluation, and training.

Question 18:

When using the Azure AI Face service, what should you use to perform one-to-many or one-to-one face matching? Each correct answer presents a complete solution.

Select all answers that apply.

  • Custom Vision
  • Face attributes
  • Face identification
  • Face verification
  • Find similar faces

Correct Answer: Face identification, Face verification

Short Explanation: Face identification and verification enable one-to-many and one-to-one face matching respectively, crucial for recognizing and verifying individuals.

Question 19:

Which service can you use to train an image classification model?

Select only one answer.

  • Azure AI Vision
  • Azure AI Custom Vision
  • Azure AI Face
  • Azure AI Language

Correct Answer: Azure AI Custom Vision

Short Explanation: Azure AI Custom Vision is tailored for training models specifically for image classification tasks.

Question 20:

Which type of artificial intelligence (AI) workload provides the ability to generate bounding boxes that identify the locations of different types of vehicles in an image?

Select only one answer.

  • Image analysis
  • Image classification
  • Optical character recognition (OCR)
  • Object detection

Correct Answer: Object detection

Short Explanation: Object detection not only identifies objects but also provides bounding boxes to locate them within images.

Question 21:

Which artificial intelligence (AI) workload scenario is an example of natural language processing (NLP)?

Select only one answer.

  • Extracting key phrases from a business insights report
  • Identifying objects in landscape images
  • Monitoring for sudden increases in the quantity of failed sign-in attempts
  • Predicting whether customers are likely to buy a product based on previous purchases

Correct Answer: Extracting key phrases from a business insights report

Short Explanation: NLP techniques like key phrase extraction analyze and process text to identify important phrases and insights.

Question 22:

Which two artificial intelligence (AI) workload scenarios are examples of natural language processing (NLP)? Each correct answer presents a complete solution.

Select all answers that apply.

  • Extracting handwritten text from online images
  • Generating tags and descriptions for images
  • Monitoring network traffic for sudden spikes
  • Performing sentiment analysis on social media data
  • Translating text between different languages from product reviews

Correct Answer: Performing sentiment analysis on social media data, Translating text between different languages from product reviews

Short Explanation: NLP is used for sentiment analysis and language translation, processing

and understanding textual content in diverse languages.

Question 23:

Which principle of responsible artificial intelligence (AI) raises awareness about the limitations of AI-based solutions?

Select only one answer.

  • Accountability
  • Privacy and security
  • Reliability and safety
  • Transparency

Correct Answer: Transparency

Short Explanation: Transparency involves clearly communicating the capabilities and limitations of AI systems to users and stakeholders.

Question 24:

Which principle of responsible artificial intelligence (AI) has the objective of ensuring that AI solutions benefit all parts of society regardless of gender or ethnicity?

Select only one answer.

  • Accountability
  • Inclusiveness
  • Privacy and security
  • Reliability and safety

Correct Answer: Inclusiveness

Short Explanation: Inclusiveness ensures AI solutions are developed and applied in ways that are fair and beneficial to all societal groups.

Question 25:

Which principle of responsible artificial intelligence (AI) involves evaluating and mitigating the bias introduced by the features of a model?

Select only one answer.

  • Accountability
  • Fairness
  • Privacy
  • Transparency

Correct Answer: Fairness

Short Explanation: Fairness in AI focuses on assessing and reducing biases to ensure equitable and unbiased model performance.

Question 26:

Which principle of responsible artificial intelligence (AI) defines the framework of governance and organization principles that meet ethical and legal standards of AI solutions?

Select only one answer.

  • Accountability
  • Fairness
  • Inclusiveness
  • Transparency

Correct Answer: Accountability

Short Explanation: Accountability involves setting up governance structures to ensure AI solutions comply with ethical and legal standards.

Question 27:

Which principle of responsible artificial intelligence (AI) plays the primary role when implementing an AI solution that meets qualifications for business loan approvals?

Select only one answer.

  • Accountability
  • Fairness
  • Inclusiveness
  • Safety

Correct Answer: Fairness

Short Explanation: Fairness ensures that AI models used for loan approvals are unbiased and provide equal opportunities for all applicants.

Question 28:

Which two principles of responsible artificial intelligence (AI) are most important when designing an AI system to manage healthcare data? Each correct answer presents part of the solution.

Select all answers that apply.

  • Accountability
  • Fairness
  • Inclusiveness
  • Privacy and security

Correct Answer: Accountability, Privacy and security

Short Explanation: Managing healthcare data with AI requires robust accountability and privacy and security measures to protect sensitive information.

Question 29:

You need to identify numerical values that represent the probability of humans developing diabetes based on age and body fat percentage.

Which type of machine learning model should you use?

Select only one answer.

  • Hierarchical clustering
  • Linear regression
  • Logistic regression
  • Multiple linear regression

Correct Answer: Multiple linear regression

Short Explanation: Multiple linear regression analyzes the relationship between multiple features (like age and body fat) and an outcome (diabetes probability).

Question 30:

Which type of machine learning algorithm predicts a numeric label associated with an item based on that item’s features?

Select only one answer.

  • Classification
  • Clustering
  • Regression
  • Unsupervised

Correct Answer: Regression

Short Explanation: Regression algorithms predict numerical values (labels) from input features, such as predicting house prices from attributes.

Question 31:

Predicting rainfall for a specific geographical location is an example of which type of machine learning?

Select only one answer.

  • Classification
  • Clustering
  • Featurization
  • Regression

Correct Answer: Regression

Short Explanation: Regression is used to predict continuous values, like the amount of rainfall in a given location.

Question 32:

A company deploys an online marketing campaign to social media platforms for a new product launch. The company wants to use machine learning to measure the sentiment of users on the Twitter platform who made posts in response to the campaign.

Which type of machine learning is this?

Select only one answer.

  • Classification
  • Clustering
  • Data transformation
  • Regression

Correct Answer: Classification

Short Explanation: Classification techniques can analyze text data to categorize sentiment as positive, negative, or neutral.

Question 33:

A healthcare organization has a dataset consisting of bone fracture scans that are categorized by using predefined fracture types. The organization wants to use machine learning to detect the different types of bone fractures for new scans before the scans are sent to a medical practitioner.

Which type of machine learning is this?

Select only one answer.

  • Classification
  • Clustering
  • Featurization
  • Regression

Correct Answer: Classification

Short Explanation: Classification identifies and assigns predefined categories, such as types of bone fractures, to new data points.

Question 34:

A company is using machine learning to predict house prices based on appropriate house attributes.

For the machine learning model, which attribute is the label?

Select only one answer.

  • Age of the house
  • Floor space size
  • Number of bedrooms
  • Price of the house

Correct Answer: Price of the house

Short Explanation: The label is the target variable that the model aims to predict, in this case, the house price.

Question 35:

A company is using machine learning to predict various aspects of its e-scooter hire service dependent on weather. This includes predicting the number of hires, the average distance traveled, and the impact on e-scooter battery levels.

For the machine learning model, which two attributes are the features? Each correct answer presents a complete solution.

Select all answers that apply.

  • Distance traveled
  • E-scooter battery levels
  • E-scooter hires
  • Weather temperature
  • Weekday or weekend

Correct Answer: Weather temperature, Weekday or weekend

Short Explanation: Features are the input variables used by the model to make predictions; in this case, weather and day type are relevant to e-scooter usage.

Question 36:

What is the purpose of a validation dataset used for as part of the development of a machine learning model?

Select only one answer.

  • Cleaning missing data
  • Evaluating the trained model
  • Feature engineering
  • Summarizing the data

Correct Answer: Evaluating the trained model

Short Explanation: A validation dataset is used to assess the performance of a machine learning model on unseen data, ensuring its generalization ability.

Question 37:

You need to create an automated machine learning (automated ML) model.

Which resource should you create first in Azure Machine Learning studio?

Select only one answer.

  • A dataset
  • A workspace
  • An Azure container instance
  • An Azure Kubernetes Service (AKS) cluster

Correct Answer: A workspace

Short Explanation: The workspace is the primary environment in Azure Machine Learning for managing and coordinating machine learning experiments and resources.

Question 38:

Which three data transformation modules are in the Azure Machine Learning designer? Each correct answer presents a complete solution.

Select all answers that apply.

  • Clean Missing Data
  • Model Evaluate Model
  • Normalize Data
  • Select Columns in Dataset
  • Train Clustering

Correct Answer: Clean Missing Data, Normalize Data, Select Columns in Dataset

Short Explanation: These modules help preprocess data by handling missing values, normalizing distributions, and selecting specific columns for training.

Question 39:

Which machine learning algorithm module in the Azure Machine Learning designer is used to train a model?

Select only one answer.

  • Clean Missing Data
  • Evaluate Model
  • Linear Regression
  • Select Columns in Dataset

Correct Answer: Linear Regression

Short Explanation: Linear Regression is an algorithm used to train models for predicting continuous numerical outcomes based on input features.

Question 40:

What is an unsupervised machine learning algorithm module for training models in the Azure Machine Learning designer?

Select only one answer.

  • Classification
  • K-Means Clustering
  • Linear Regression
  • Normalize Data

Correct Answer: K-Means Clustering

Short Explanation: K-Means Clustering is an unsupervised algorithm that groups data points into clusters based on similarity without predefined labels.

Question 41:

Which natural language processing (NLP) technique normalizes words before counting them?

Select only one answer.

  • Frequency analysis
  • N-grams
  • Stemming
  • Vectorization

Correct Answer: Stemming

Short Explanation: Stemming reduces words to their root forms, normalizing variations before counting or analyzing them in text processing.

Question 42:

What is the first step in the statistical analysis of terms in a text in the context of natural language processing (NLP)?

Select only one answer.

  • Creating a vectorized model
  • Counting the occurrences of each word
  • Encoding words as numeric features
  • Removing stop words

Correct Answer: Counting the occurrences of each word

Short Explanation: Initial text analysis often involves counting word occurrences to understand frequency and importance within the text.

Question 43:

Which two Azure AI Services features can be used to enable both text-to-text and speech-to-text between multiple languages? Each correct answer presents part of the solution.

Select all answers that apply.

  • Conversational Language Understanding
  • Key phrase extraction
  • Language detection
  • The Speech service
  • The Translator service

Correct Answer: The Speech service, The Translator service

Short Explanation: The Speech and Translator services in Azure AI enable translation and conversion between text and speech in multiple languages.

Question 44:

Which two features of Azure AI Services allow you to identify issues from support question data, as well as identify any people and products that are mentioned? Each correct answer presents part of the solution.

Select all answers that apply.

  • Azure AI Bot Service
  • Conversational Language Understanding
  • Key phrase extraction
  • Named entity

recognition

  • Azure AI Speech service

Correct Answer: Key phrase extraction, Named entity recognition

Short Explanation: Key phrase extraction identifies core issues in support data, while named entity recognition pinpoints mentions of specific people and products.

Question 45:

Which Azure AI Service for Language feature allows you to analyze written articles to extract information and concepts, such as people and locations, for classification purposes?

Select only one answer.

  • Azure AI Content Moderator
  • Key phrase extraction
  • Named entity recognition
  • Personally Identifiable Information (PII) detection

Correct Answer: Named entity recognition

Short Explanation: Named entity recognition (NER) extracts entities like people and locations from text, facilitating information classification.

Question 46:

Which three values are returned by the language detection feature of the Azure AI Language service in Azure? Each correct answer presents part of the solution.

Select all answers that apply.

  • Bounding box coordinates
  • ISO 6391 Code
  • Language Name
  • Score
  • Wikipedia URL

Correct Answer: ISO 6391 Code, Language Name, Score

Short Explanation: Language detection identifies the language of the text, providing the ISO code, name, and confidence score of the detected language.

Question 47:

For which two scenarios is the Universal Language Model used by the speech-to-text API optimized? Each correct answer presents a complete solution.

Select all answers that apply.

  • Acoustic
  • Conversational
  • Dictation
  • Language
  • Pronunciation

Correct Answer: Conversational, Dictation

Short Explanation: The Universal Language Model is tailored to handle natural conversational speech and dictation, making it suitable for diverse speaking styles.

Question 48:

Which feature of the Azure AI Translator service is available only to Custom Translator?

Select only one answer.

  • Document translation
  • Model training with a dictionary
  • Speaker recognition
  • Text translation

Correct Answer: Model training with a dictionary

Short Explanation: Custom Translator allows for the training of models with specialized dictionaries, enabling more accurate and context-specific translations.

Question 49:

When using the Azure AI Service for Language, what should you use to provide further information online about entities extracted from a text?

Select only one answer.

  • Entity linking
  • Key phrase extraction
  • Named entity recognition
  • Text translation

Correct Answer: Entity linking

Short Explanation: Entity linking associates extracted entities with relevant information and sources online, enriching the context and understanding of the data.

Question 50:

Which computer vision solution provides the ability to identify a person's age based on a photograph?

Select only one answer.

  • facial detection
  • image classification
  • object detection
  • semantic segmentation

Correct Answer: facial detection
Short Explanation: Facial detection can analyze facial features to estimate a person’s age.

Question 51:

Which two specialized domain models are supported by Azure AI Vision when categorizing an image? Each correct answer presents a complete solution.

Select all answers that apply.

  • celebrities
  • image types
  • landmarks
  • people_
  • people_group

Correct Answers: landmarks, celebrities
Short Explanation: Azure AI Vision can categorize images by identifying landmarks and recognizing celebrities using its domain models.

Question 52:

Which computer vision service provides bounding coordinates as part of its output?

Select only one answer.

  • image analysis
  • image classification
  • object detection
  • semantic segmentation

Correct Answer: object detection
Short Explanation: Object detection outputs bounding boxes to specify the location of objects within an image.

Question 53:

Which process allows you to use optical character recognition (OCR)?

Select only one answer.

  • digitizing medical records
  • identifying access control for a laptop
  • identifying wildlife in an image
  • translating speech to text

Correct Answer: digitizing medical records
Short Explanation: OCR is used to convert written or printed text into digital form, useful for digitizing medical records.

Question 54:

What allows you to identify different types of bone fractures in X-ray images?

Select only one answer.

  • conversational artificial intelligence (AI)
  • facial detection
  • image classification
  • object detection

Correct Answer: image classification
Short Explanation: Image classification can categorize different types of bone fractures based on visual patterns in X-ray images.

Question 55:

What allows you to identify different vehicle types in traffic monitoring images?

Select only one answer.

  • image classification
  • linear regression
  • object detection
  • optical character recognition (OCR)

Correct Answer: object detection
Short Explanation: Object detection identifies and locates different types of vehicles in images by assigning bounding boxes to them.

Question 56:

What can be used for an attendance system that can scan handwritten signatures?

Select only one answer.

  • face detection
  • image classification
  • object detection
  • optical character recognition (OCR)

Correct Answer: optical character recognition (OCR)
Short Explanation: OCR is capable of converting handwritten signatures into digital text for record-keeping.

Question 57:

Which feature of computer vision involves associating an image with metadata that summarizes the attributes of the image?

Select only one answer.

  • categorizing
  • content organization
  • detecting image types
  • tagging

Correct Answer: tagging
Short Explanation: Tagging involves assigning metadata labels to an image, summarizing its contents and attributes.

Question 58:

Which analytical task of the Azure AI Vision service returns bounding box coordinates?

Select only one answer.

  • image categorization
  • object detection
  • optical character recognition (OCR)
  • tagging

Correct Answer: object detection
Short Explanation: Object detection identifies objects within an image and provides bounding box coordinates to define their locations.

Question 59:

When using the Azure AI Face service, what should you use to perform one-to-many or one-to-one face matching? Each correct answer presents a complete solution.

Select all answers that apply.

  • Custom Vision
  • face attributes
  • face identification
  • face verification
  • find similar faces

Correct Answers: face identification, face verification, find similar faces
Short Explanation: Face identification and face verification are used to match faces in one-to-one or one-to-many scenarios, and "find similar faces" helps in finding faces that closely match a given face.

Question 60:

You need to identify numerical values that represent the probability of humans developing diabetes based on age and body fat percentage.

Which type of machine learning model should you use?

Select only one answer.

  • hierarchical clustering
  • linear regression
  • logistic regression
  • multiple linear regression

Correct Answer: linear regression
Short Explanation: Linear regression models predict numerical outcomes, such as the probability of developing diabetes based on continuous variables like age and body fat percentage.

Question 61:

Which type of machine learning algorithm assigns items to a set of predefined categories?

Select only one answer.

  • classification
  • clustering
  • regression
  • unsupervised

Correct Answer: classification
Short Explanation: Classification algorithms assign items to predefined categories based on their features.

Question 62:

A healthcare organization has a dataset consisting of bone fracture scans that are categorized by using predefined fracture types. The organization wants to use machine learning to detect the different types of bone fractures for new scans before the scans are sent to a medical practitioner.

Which type of machine learning is this?

Select only one answer.

  • classification
  • clustering
  • featurization
  • regression

Correct Answer: classification
Short Explanation: Classification is used to predict the category or type, in this case, the type of bone fractures, based on the data provided.

Question 63:

You plan to use machine learning to predict the probability of humans developing diabetes based on their age and body fat percentage.

What should the model include?

Select only one answer.

  • three features
  • three labels
  • two features and one label
  • two labels and one feature

Correct Answer: two features and one label
Short Explanation: The model should include two features (age and body fat percentage) and one label (the probability of developing diabetes).

Question 64:

Which feature makes regression an example of supervised machine learning?

Select only one answer.

  • use of historical data with known label values to train a model
  • use of historical data with unknown label values to train a model
  • use of randomly generated data with known label values to train a model
  • use of randomly generated data with unknown label values to train a model

Correct Answer: use of historical data with known label values to train a model
Short Explanation: Supervised learning uses historical data with known outcomes (labels) to train models to predict future outcomes.

Question 65:

In a regression machine learning algorithm, what are the characteristics of features and labels in a training dataset?

Select only one answer.

  • known feature and label values
  • known feature values and unknown label values
  • unknown feature and label values
  • unknown feature values and known label values

Correct Answer: known feature and label values
Short Explanation: Both features and labels must be known in a training dataset for supervised learning algorithms like regression.

Question 66:

A company is using machine learning to predict various aspects of its e-scooter hire service dependent on weather. This includes predicting the number of hires, the average distance traveled, and the impact on e-scooter battery levels.

For the machine learning model, which two attributes are the features? Each correct answer presents a complete solution.

Select all answers that apply.

  • distance traveled
  • e-scooter battery levels
  • e-scooter hires
  • weather temperature
  • weekday or weekend

Correct Answers: weather temperature, weekday or weekend
Short Explanation: Features are input variables used to predict the target outcomes, such as weather temperature and whether it is a weekday or weekend.

Question 67:

What is the purpose of a validation dataset used for as part of the development of a machine learning model?

Select only one answer.

  • cleaning missing data
  • evaluating the trained model
  • feature engineering
  • summarizing the data

Correct Answer: evaluating the trained model
Short Explanation: A validation dataset is used to assess the performance of the model after training, ensuring it generalizes well to new data.

Question 68:

You need to use Azure Machine Learning to train a regression model.

What should you create in Machine Learning studio?

Select only one answer.

  • a job
  • a workspace
  • an Azure container instance
  • an Azure Kubernetes Service (AKS) cluster

Correct Answer: a job
Short Explanation: A job in Azure Machine Learning studio represents a task that runs machine learning algorithms on data.

Question 69:

You need to use the Azure Machine Learning designer to train a machine learning model.

What should you do first in the Machine Learning designer?

Select only one answer.

  • Add a dataset.
  • Add training modules.
  • Create a pipeline.
  • Deploy a service.

Correct Answer: Add a dataset.
Short Explanation: The first step in designing a machine learning model in Azure Machine Learning designer is to add a dataset for the model to learn from.

Question 70:

You train a regression model by using automated machine learning (automated ML) in the Azure Machine Learning studio. You review the best model summary.

You need to publish the model for others to use from the internet.

What should you do next?

Select only one answer.

  • Create a compute cluster.
  • Deploy the model to an endpoint.
  • Split the data into training and validation datasets.
  • Test the deployed service.

Correct Answer: Deploy the model to an endpoint.
Short Explanation: Deploying the model to an endpoint makes it accessible for others to use through an API or web service.

Question 71:

Which three supervised machine learning models can you train by using automated machine learning (automated ML) in the Azure Machine Learning studio? Each correct answer presents a complete solution.

Select all answers that apply.

  • Classification
  • Clustering
  • inference pipeline
  • regression
  • time-series forecasting

Correct Answers: Classification, regression, time-series forecasting
Short Explanation: Automated ML in Azure can train models

for classification, regression, and time-series forecasting tasks.

Question 72:

Which natural language processing (NLP) technique normalizes words before counting them?

Select only one answer.

  • frequency analysis
  • N-grams
  • stemming
  • vectorization

Correct Answer: stemming
Short Explanation: Stemming reduces words to their base or root form, which is essential for normalizing before counting.

Question 73:

What is the first step in the statistical analysis of terms in a text in the context of natural language processing (NLP)?

Select only one answer.

  • creating a vectorized model
  • counting the occurrences of each word
  • encoding words as numeric features
  • removing stop words

Correct Answer: counting the occurrences of each word
Short Explanation: The initial step in text analysis is to count the frequency of each word, which helps in understanding the text's structure and content.

Question 74:

What is the confidence score returned by the Azure AI Language detection service of natural language processing (NLP) for an unknown language name?

Select only one answer.

  • 1
  • -1
  • NaN
  • Unknown

Correct Answer: NaN
Short Explanation: NaN (Not a Number) indicates that the service cannot assign a confidence score for an unrecognized or unknown language.

Question 75:

Which Azure AI Service for Language feature can be used to analyze online user reviews to identify whether users view a product positively or negatively?

Select only one answer.

  • key phrase extraction
  • language detection
  • named entity recognition
  • sentiment analysis

Correct Answer: sentiment analysis
Short Explanation: Sentiment analysis evaluates text to determine the sentiment or emotional tone, such as positive or negative reviews.

Question 76:

Which two Azure AI Services features can be used to enable both text-to-text and speech-to-text between multiple languages? Each correct answer presents part of the solution.

Select all answers that apply.

  • Conversational Language Understanding
  • key phrase extraction
  • language detection
  • the Speech service
  • the Translator service

Correct Answers: the Speech service, the Translator service
Short Explanation: The Speech service supports speech-to-text translation, and the Translator service handles text-to-text translation between multiple languages.

Question 77:

Which two features of Azure AI Services allow you to identify issues from support question data, as well as identify any people and products that are mentioned? Each correct answer presents part of the solution.

Select all answers that apply.

  • Azure AI Bot Service
  • Conversational Language Understanding
  • key phrase extraction
  • named entity recognition
  • Azure AI Speech service

Correct Answers: key phrase extraction, named entity recognition
Short Explanation: Key phrase extraction identifies main issues in text, and named entity recognition detects specific entities like people and products.

Question 78:

Which Azure resource provides direct access to both Azure AI Translator and Azure AI Speech services through a single endpoint and authentication key?

Select only one answer.

  • Azure AI Bot Service
  • Azure AI Services
  • Azure Machine Learning
  • Azure AI Language service

Correct Answer: Azure AI Services
Short Explanation: Azure AI Services provides unified access to various AI capabilities, including Translator and Speech services, through a single endpoint and authentication.

Question 79:

Which three features are elements of the Azure AI Speech service? Each correct answer presents a complete solution.

Select all answers that apply.

  • document translation
  • language identification
  • speaker recognition
  • text translation
  • voice assistants

Correct Answers: language identification, speaker recognition, voice assistants
Short Explanation: The Azure AI Speech service includes features like identifying spoken languages, recognizing individual speakers, and supporting voice assistants.

Question 80:

Which feature of the Azure AI Speech service can identify distinct user voices?

Select only one answer.

  • language identification
  • speech recognition
  • speech synthesis
  • speech translation

Correct Answer: speaker recognition
Short Explanation: Speaker recognition can differentiate between voices to identify distinct users.

Question 81:

Which natural language processing (NLP) workload is used to generate closed caption text for live presentations?

Select only one answer.

  • Azure AI Speech
  • conversational language understanding (CLU)
  • question answering models
  • text analysis

Correct Answer: Azure AI Speech
Short Explanation: Azure AI Speech can transcribe spoken words into text in real-time, suitable for generating closed captions during live presentations.

Question 82:

Which type of artificial intelligence (AI) workload provides the ability to generate bounding boxes that identify the locations of different types of vehicles in an image?

Select only one answer.

  • image analysis
  • image classification
  • optical character recognition (OCR)
  • object detection

Correct Answer: object detection
Short Explanation: Object detection identifies and locates objects, such as vehicles, in an image by generating bounding boxes around them.

Question 83:

Which type of service provides a platform for conversational artificial intelligence (AI)?

Select only one answer.

  • Azure AI Bot Service
  • Azure AI Document Intelligence
  • Azure AI Vision
  • Azure AI Translator

Correct Answer: Azure AI Bot Service
Short Explanation: Azure AI Bot Service provides tools and frameworks to develop conversational AI applications like chatbots.

Question 84:

Which AI service can be integrated into chat applications and generate content in the form of text?

Select only one answer.

  • Azure AI Language
  • Azure AI Metrics Advisor
  • Azure AI Vision
  • Azure OpenAI

Correct Answer: Azure OpenAI
Short Explanation: Azure OpenAI can generate text content, making it suitable for integration into chat applications to create responses.

Question 85:

Which type of artificial intelligence (AI) workload has the primary purpose of making large amounts of data searchable?

Select only one answer.

  • image analysis
  • knowledge mining
  • object detection
  • semantic segmentation

Correct Answer: knowledge mining
Short Explanation: Knowledge mining extracts useful information from large datasets, making it searchable and actionable.

Question 86:

Which two artificial intelligence (AI) workload scenarios are examples of natural language processing (NLP)? Each correct answer presents a complete solution.

Select all answers that apply.

  • extracting handwritten text from online images
  • generating tags and descriptions for images
  • monitoring network traffic for sudden spikes
  • performing sentiment analysis on social media data
  • translating text between different languages from product reviews

Correct Answers: performing sentiment analysis on social media data, translating text between different languages from product reviews
Short Explanation: NLP includes analyzing text to determine sentiment and translating text between different languages.

Question 87:

Which principle of responsible artificial intelligence (AI) raises awareness about the limitations of AI-based solutions?

Select only one answer.

  • accountability
  • privacy and security
  • reliability and safety
  • transparency

Correct Answer: transparency
Short Explanation: Transparency involves providing insights into how AI systems make decisions and their potential limitations.

Question 88:

Which principle of responsible artificial intelligence (AI) has the objective of ensuring that AI solutions benefit all parts of society regardless of gender or ethnicity?

Select only one answer.

  • accountability
  • inclusiveness
  • privacy and security
  • reliability and safety

Correct Answer: inclusiveness
Short Explanation: Inclusiveness ensures that AI systems are designed to benefit all individuals and groups fairly.

Question 89:

Which two principles of responsible artificial intelligence (AI) are most important when designing an AI system to manage healthcare data? Each correct answer presents part of the solution.

Select all answers that apply.

  • accountability
  • fairness
  • inclusiveness
  • privacy and security

Correct Answers: accountability, privacy and security
Short Explanation: Accountability ensures the AI system adheres to ethical standards, while privacy and security protect sensitive healthcare data.

Question 90:

Which principle of responsible artificial intelligence (AI) ensures that an AI system meets any legal and ethical standards it must abide by?

Select only one answer.

  • accountability
  • fairness
  • inclusiveness
  • privacy and security

Correct Answer: accountability
Short Explanation: Accountability involves ensuring that AI systems comply with legal and ethical requirements.

Question 91:

Which three sources can be used to generate questions and answers for a knowledge base? Each correct answer presents a complete solution.

Select all answers that apply.

  • a webpage
  • an audio file
  • an existing FAQ document
  • an image file
  • manually entered data

Correct Answers: a webpage, an existing FAQ document, manually entered data
Short Explanation: Knowledge bases can be created using text from webpages, pre-existing FAQs, and manually entered data to provide accurate answers.

Question 92:

Select the answer that correctly completes the sentence.

[Answer choice] use plugins to provide end users with the ability to get help with common tasks from a generative AI model.

Select only one answer.

  • Copilots
  • Language Understanding solutions
  • Question answering models
  • RESTful API services

Correct Answer: Copilots
Short Explanation: Copilots integrate with applications to assist users by performing tasks using generative AI capabilities.

Question 93:

At which layer can you apply content filters to suppress prompts and responses for a responsible generative AI solution?

Select only one answer.

  • metaprompt and grounding
  • model
  • safety system
  • user experience

Correct Answer: safety system
Short Explanation: The safety system layer can apply filters to ensure that AI responses adhere to safety and content guidelines.

Question 94:

Select the answer that correctly completes the sentence.

[Answer choice] can return responses, such as natural language, images, or code, based on natural language input.

Select only one answer.

  • Computer vision

  • Deep learning

  • Generative AI

  • Machine learning

  • Reinforcement learning

Correct Answer: Generative AI
Short Explanation: Generative AI models can produce responses in various forms like text, images, or code from natural language inputs.

Question 95:

Select the answer that correctly completes the sentence.

[Answer choice] can be used to identify constraints and styles for the responses of a generative AI model.

Select only one answer.

  • Data grounding
  • Embeddings
  • System messages
  • Tokenization

Correct Answer: System messages
Short Explanation: System messages set rules and styles to guide how a generative AI model should respond.

Question 96:

Select the answer that correctly completes the sentence.

[Answer choice] can be used to identify constraints and styles for the responses of a generative AI model.

Select only one answer.

  • Data grounding
  • Embeddings
  • System messages
  • Tokenization

Correct Answer: System messages
Short Explanation: System messages dictate the constraints and guidelines for the output responses of a generative AI model.

Question 97:

Which two capabilities are examples of a GPT model? Each correct answer presents a complete solution.

Select all answers that apply.

  • Create natural language.
  • Detect specific dialects of a language.
  • Generate closed captions in real-time from a video.
  • Synthesize speech.
  • Understand natural language.

Correct Answers: Create natural language, Understand natural language
Short Explanation: GPT models excel in generating and understanding natural language, facilitating tasks like text completion and comprehension.

Question 98:

You plan to develop an image processing solution that will use DALL-E as a generative AI model.

Which capability is NOT supported by the DALL-E model?

Select only one answer.

  • image description
  • image editing
  • image generation
  • image variations

Correct Answer: image description
Short Explanation: DALL-E generates and edits images based on prompts but does not provide descriptive text for images.

Question 99:

Which generative AI model is used to generate images based on natural language prompts?

Select only one answer.

  • DALL-E
  • Embeddings
  • GPT-3.5
  • GPT-4
  • Whisper

Correct Answer: DALL-E
Short Explanation: DALL-E generates images from textual descriptions, allowing users to create visuals based on their prompts.

Question 100:

Select the answer that correctly completes the sentence.

[Answer choice] can search, classify, and compare sources of text for similarity.

Select only one answer.

  • Data grounding
  • Embeddings
  • Machine learning
  • System messages

Correct Answer: Embeddings
Short Explanation: Embeddings represent text in a numerical format that can be used to search, classify, and compare text for similarity.