Explanation:

The correct completion of the sentence is:
"You can use the Custom Vision service to train an object detection model by using your own images." According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module "Identify features of computer vision workloads," the Azure Custom Vision service is a specialized component of Azure Cognitive Services for Vision that enables developers to train custom image classification or object detection models using their own labeled image datasets.
The Custom Vision service differs from the Computer Vision service in that it allows full customization - meaning you can upload your own images, tag them manually, and train the model to recognize objects specific to your use case (for example, detecting your company's products, tools, or vehicles). Once trained, the model can identify and localize these objects in new images by returning bounding boxes and confidence scores, which is precisely what defines an object detection workload.
Microsoft's AI-900 materials describe object detection as the process of identifying objects in an image and determining their position, typically represented by bounding boxes. Custom Vision supports two main project types:
* Image Classification: Determines what is present in the image (e.g., "dog," "cat," "car").
* Object Detection: Identifies what is present and where it is located in the image.
In contrast:
* Computer Vision provides prebuilt models for general image analysis but doesn't allow custom model training.
* Form Recognizer is used for extracting text and data from structured or semi-structured documents.
* Azure Video Analyzer for Media focuses on video content analysis, not custom object detection.
Therefore, based on the official Microsoft AI-900 study guide and Microsoft Learn content, the verified and correct answer is Custom Vision, as it specifically allows training of a custom object detection model using your own images.

Explanation:
Description
Correct Service
Enables the use of natural language to query a knowledge base.
QnA Maker
Enables the real-time transcription of speech-to-text.
Speech
This question tests understanding of Azure Cognitive Services and their use cases as outlined in the Microsoft Azure AI Fundamentals (AI-900) study guide.
* "Enables the use of natural language to query a knowledge base." # QnA MakerAccording to Microsoft Learn's AI-900 module "Identify features of Natural Language Processing (NLP) workloads and services," QnA Maker is a cloud-based service that allows developers to build a question-and-answer layer over structured or unstructured content. It enables users to ask questions in natural language, and the service retrieves the most relevant answer from a knowledge base (such as FAQs, manuals, or documents).QnA Maker uses Natural Language Processing (NLP) techniques to interpret user intent and return an appropriate response. It is often integrated into chatbots built with Azure Bot Service to make them capable of conversational question-answering. In the newer Azure Cognitive Services lineup, QnA Maker capabilities are merged into Azure Cognitive Service for Language (Question Answering).
* "Enables the real-time transcription of speech-to-text." # SpeechThe Azure Speech service (part of Azure Cognitive Services) provides the ability to convert spoken language into written text in real time.
This feature, called Speech-to-Text, uses deep neural network models to recognize and transcribe human speech with high accuracy.Microsoft's AI-900 documentation specifies that Speech service capabilities also include text-to-speech, speech translation, and speaker recognition. Real-time transcription is widely used in applications such as voice assistants, captioning systems, call analytics, and accessibility tools.
Other listed services such as Azure Storage and Language Understanding (LUIS) serve different purposes:
* Azure Storage handles data storage, not AI workloads.
* LUIS identifies user intent from natural language but does not query knowledge bases directly.

Explanation:

This question is based on identifying Natural Language Processing (NLP) workloads, which is a fundamental topic in the Microsoft Azure AI Fundamentals (AI-900) certification. According to the official Microsoft Learn module "Describe features of natural language processing (NLP) workloads on Azure", NLP enables computers to understand, interpret, and generate human language - both written and spoken.
* A bot that responds to queries by internal users - YesThis is an example of a natural language processing workload because it involves understanding and generating human language. A chatbot interprets user input (queries written or spoken) using language understanding and text analytics, and then produces appropriate responses. On Azure, this can be implemented using Azure AI Language (LUIS) and the Azure Bot Service, both core NLP technologies.
* A mobile application that displays images relating to an entered search term - NoThis application involves searching for or displaying images, which falls under the computer vision workload, not NLP.
Computer vision focuses on analyzing and interpreting visual data like photos or videos, while NLP deals with language and text processing.
* A web form used to submit a request to reset a password - NoA password reset form involves structured input fields and user authentication, not natural language understanding or generation. It's part of standard web development and identity management, not an NLP-related process.
Therefore, based on Microsoft's AI-900 curriculum definitions:
# The only true NLP example is the bot responding to user queries, since it processes and understands natural language input to generate conversational output.

Explanation:

According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module "Identify features of common machine learning types", the term features refers to the input variables or independent variables used by a machine learning model to make predictions. These are the measurable properties or attributes of the data that influence the output (target) value.
In a supervised learning process, data is typically divided into two parts:
* Features # The input variables used by the model to learn patterns (e.g., customer age, income, credit score).
* Label (Target) # The outcome or value the model is trying to predict (e.g., whether a loan will be approved or the amount of a house price).
During training, the model uses the features to understand how input data correlates with the target output.
Once trained, the model applies the same learned relationships to predict outcomes for new, unseen data using only the features.
For example:
* In a regression model predicting house prices, features might include square footage, number of bedrooms, and location.
* In a classification model predicting loan approval, features might include applicant income, credit score, and debt ratio.
To contrast with other options:
* Dependent variables (or labels) are the outcomes the model predicts.
* Identifiers (like customer IDs) are unique values that do not help the model learn relationships and are typically excluded from features.
* Labels are the target outputs, not the inputs.
Therefore, in Azure Machine Learning and AI-900 terminology, data values used to make a prediction are called "features."

According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module "Identify features of regression machine learning", regression is the machine learning technique used when the goal is to predict a continuous numeric value based on historical data. In this question, predicting the number of gift cards that will be sold next month involves forecasting a quantity-a numeric outcome- which is the hallmark of a regression problem.
Regression models learn patterns from past data (for example, previous months' gift card sales, seasonality, holidays, and marketing spend) and use that information to predict future sales. Common algorithms used for regression include linear regression, decision tree regression, and boosted regression trees. The output is a continuous value such as "2,450 gift cards expected next month." In contrast:
* A. Classification is used when the output is categorical, such as predicting whether a transaction is
"fraud" or "not fraud," or whether a customer will "renew" or "cancel." It answers questions with discrete classes rather than numeric values.
* C. Clustering is an unsupervised learning technique used to group similar data points together based on their characteristics-for example, segmenting customers into behavior-based clusters. Clustering doesn't predict future numeric outcomes.
The AI-900 curriculum explicitly explains that regression predicts numeric values, classification predicts categories, and clustering finds natural groupings in data.
Therefore, to predict the number of gift cards to be sold, the correct and verified machine learning type is Regression.
Final answer: B. Regression
Reference:Microsoft Learn - Identify the types of machine learning models: Regression, Classification, and Clustering (AI-900 Learning Path)