AI-900 無料問題集「Microsoft Azure AI Fundamentals」
To complete the sentence, select the appropriate option in the answer area.
正解：
Explanation:
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module "Explore fundamental principles of machine learning", feature engineering is the process used to generate additional features or transform existing data into forms that improve model performance. Features are individual measurable properties or characteristics used as input for machine learning algorithms. The goal of feature engineering is to create new informative variables that better represent the underlying patterns in the data.
Feature engineering may include tasks such as:
* Combining or transforming raw data columns (e.g., creating a "total purchase amount" from price × quantity).
* Extracting time-based components (e.g., year, month, day, hour) from datetime values.
* Encoding categorical variables (e.g., one-hot encoding or label encoding).
* Scaling or normalizing numerical features.
* Creating polynomial or interaction terms to capture complex relationships.
Microsoft's AI-900 learning material emphasizes that the process of preparing data for machine learning involves data cleaning, feature engineering, and feature selection. While feature selection is about choosing the most relevant features from the existing dataset, feature engineering focuses on creating or generating new features to enhance model accuracy and generalization.
The other options do not fit this definition:
* Feature selection is about removing redundant or irrelevant features, not generating new ones.
* Model evaluation involves assessing the model's performance using metrics like accuracy or F1 score.
* Model training is the phase where the algorithm learns patterns from the data, not when features are created.
Therefore, based on the AI-900 official concepts and Microsoft's documentation, the correct answer is Feature engineering, as it is the process specifically used to generate additional features that improve machine learning model performance and predictive capability.
To complete the sentence, select the appropriate option in the answer area.
正解：
Explanation:
Features
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module "Explore fundamental principles of machine learning," data values that influence the prediction of a model are called features. In the context of machine learning, a feature is an individual measurable property, attribute, or input variable used by the model to make predictions.
Features are the independent variables that describe the characteristics of the data. For example, in a housing price prediction model, features might include square footage, location, number of bedrooms, and year built.
These inputs help the model understand relationships in the data so it can predict the target outcome (the house price).
Microsoft Learn explains that features are the input variables that the algorithm uses to identify patterns and relationships in the training data. During training, the model learns how changes in these features influence the label (also known as the dependent variable or target variable). The label is the value the model tries to predict-such as "price," "category," or "yes/no." Here's how the other options differ:
* Dependent variables (labels): These are the outcomes or target values the model predicts, not the inputs.
* Identifiers: These are unique keys (like customer ID or transaction ID) used to distinguish records but not to influence predictions.
* Labels: As mentioned, labels are the results the model tries to predict.
Therefore, based on the AI-900 learning objectives and Microsoft's official explanation, the data values that influence the prediction of a model-that is, the input variables that guide the model's learning-are called features. These features form the foundation of the model's predictive capabilities and directly impact its accuracy and performance.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
NOTE: Each correct selection is worth one point.
正解：
Explanation:
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module "Identify features of common machine learning types", there are three main types of machine learning: supervised learning, unsupervised learning, and reinforcement learning. Within supervised learning, two common approaches are regression and classification, while clustering is a primary example of unsupervised learning.
* "You train a regression model by using unlabeled data." - No.Regression models are trained with labeled data, meaning the input data includes both features (independent variables) and target labels (dependent variables) representing continuous numerical values. Examples include predicting house prices or sales forecasts. Unlabeled data (data without target output values) cannot be used to train regression models; such data is used in unsupervised learning tasks like clustering.
* "The classification technique is used to predict sequential numerical data over time." - No.
Classification is used for categorical predictions, where outputs belong to discrete classes, such as spam
/not spam or disease present/absent. Predicting sequential numerical data over time refers to time series forecasting, which is typically a regression or forecasting problem, not classification. The AI-900 syllabus clearly separates classification (categorical prediction) from regression (continuous value prediction) and time series (temporal pattern analysis).
* "Grouping items by their common characteristics is an example of clustering." - Yes.This statement is correct. Clustering is an unsupervised learning technique used to group similar data points based on their features. The AI-900 study materials describe clustering as the process of "discovering natural groupings in data without predefined labels." Common examples include customer segmentation or document grouping.
Therefore, based on Microsoft's AI-900 training objectives and definitions:
* Regression # supervised learning using labeled continuous data (No)
* Classification # categorical prediction, not sequential numeric forecasting (No)
* Clustering # grouping by similarity (Yes)
You have an app that identifies birds in images. The app performs the following tasks:
* Identifies the location of the birds in the image
* Identifies the species of the birds in the image
Which type of computer vision does each task use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
* Identifies the location of the birds in the image
* Identifies the species of the birds in the image
Which type of computer vision does each task use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
正解：
Explanation:
According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module "Explore computer vision in Microsoft Azure," there are multiple types of computer vision tasks, each designed for different goals such as recognizing, categorizing, or locating objects within an image.
In this question, the application performs two distinct tasks: locating birds within an image and identifying their species. Each of these corresponds to a different type of computer vision capability.
* Locate the birds # Object detection
* Object detection is used when an AI system needs to identify and locate multiple objects within a single image.
* It not only recognizes what the object is but also provides bounding boxes that indicate the exact position of each object.
* In this scenario, locating the birds (drawing rectangles around each bird) is achieved through object detection models, such as those available in the Azure Custom Vision Object Detection domain.
* Identify the species of the birds # Image classification
* Image classification focuses on identifying what is in the image rather than where it is.
* It assigns a single label (or multiple labels in multilabel classification) to an entire image based on its contents.
* In this case, determining the species of a bird (e.g., robin, eagle, parrot) is achieved through image classification, where the model compares visual features against learned patterns from training data.
Incorrect options:
* Automated captioning generates descriptive sentences about an image, not object locations or classifications.
* Optical character recognition (OCR) extracts text from images, irrelevant in this case.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
NOTE: Each correct selection is worth one point.
正解：
Explanation:
The correct answers are Yes, Yes, and Yes.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn content in the section "Describe features of conversational AI workloads on Azure", bots created using Azure Bot Service can interact with users across multiple channels. The AI-900 syllabus explains that Azure Bot Service integrates with various communication platforms, allowing developers to build a single bot that can be deployed in many contexts without rewriting the logic.
* "You can communicate with a bot by using Cortana." - Yes.The AI-900 learning materials explain that Cortana, Microsoft's intelligent personal assistant, can serve as a channel for bots built with the Azure Bot Service. Through the Bot Framework, bots can be connected to Cortana to allow users to interact via voice or text. Although Cortana is less prominent now, it remains conceptually included in the AI-
900 coverage as an example of a voice-based conversational AI channel.
* "You can communicate with a bot by using Microsoft Teams." - Yes.This statement is true and directly referenced in the AI-900 syllabus. Microsoft Teams is a fully supported communication channel for Azure Bot Service. Bots in Teams can handle chat messages, commands, and interactions in team or personal contexts. The Microsoft Learn materials specify Teams as one of the native connectors where enterprise users can interact with organizational bots.
* "You can communicate with a bot by using a webchat interface." - Yes.This is also true. The Web Chat channel is one of the most common ways to deploy bots publicly. Azure Bot Service provides a Web Chat control that can be embedded directly into a webpage or web application. This allows users to interact with the bot using a chat window, just like on customer service websites.
Therefore, all three interfaces-Cortana (voice-based), Microsoft Teams (enterprise chat), and Web Chat (browser-based)-are valid and officially supported communication channels for Azure bots.