AI Quiz Q.docx PDF

\ **Answer: Labeling** Ensuring that the numeric variables in training data are on a similar scale is an example of \_\_\_\_\_\_\_\_\_\_. A. data ingestion.\ B. feature engineering.\ **C. feature selection.**\ D. model training. Which three sources can be used to generate questions a...

\ **Answer: Labeling** Ensuring that the numeric variables in training data are on a similar scale is an example of \_\_\_\_\_\_\_\_\_\_. A. data ingestion.\ B. feature engineering.\ **C. feature selection.**\ D. model training. 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 **This answer is correct.** an audio file an existing FAQ document **This answer is correct.** an image file manually entered data **This answer is correct.** A webpage or an existing document, such as a text file containing question and answer pairs, can be used to generate a knowledge base. You can also manually enter the knowledge base question-and-answer pairs. You cannot directly use an image or an audio file to import a knowledge base. 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 **This answer is correct.** Language Understanding solutions Question answering models RESTful API services Copilots are often integrated into applications to provide a way for users to get help with common tasks from a generative AI model. Copilots are based on a common architecture, so developers can build custom copilots for various business-specific applications and services. 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 **This answer is correct.** user experience The safety system layer includes platform-level configurations and capabilities that help mitigate harm. For example, the Azure OpenAI service includes support for content filters that apply criteria to suppress prompts and responses based on the classification of content into four severity levels (safe, low, medium, and high) for four categories of potential harm (hate, sexual, violence, and self-harm). 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 **This answer is correct.** Machine learning Reinforcement learning Generative AI models offer the capability of generating images based on a prompt by using DALL-E models, such as generating images from natural language. The other AI capabilities are used in different contexts to achieve other goals. Which natural language processing (NLP) workload is used to generate closed caption text for live presentations? Select only one answer. Azure AI Speech **This answer is correct.** conversational language understanding (CLU) question answering models text analysis 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 **This answer is correct.** object detection semantic segmentation Knowledge mining is an artificial intelligence (AI) workload that has the purpose of making large amounts of data searchable. While other workloads leverage indexing for faster access to large amounts of data, this is not their primary purpose. 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 **This answer is correct.** identifying objects in landscape images monitoring for sudden increases in quantity of failed sign-in attempts predicting whether customers are likely to buy a product based on previous purchases 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 **This answer is incorrect.** generating tags and descriptions for images monitoring network traffic for sudden spikes performing sentiment analysis on social media data **This answer is correct.** translating text between different languages from product reviews **This answer is correct.** Which two artificial intelligence (AI) workload features are part of the Azure AI Vision service? Each correct answer presents a complete solution. Select all answers that apply. entity recognition key phrase extraction optical character recognition (OCR) **This answer is correct.** sentiment analysis spatial analysis **This answer is correct.** 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 **This answer is incorrect.** transparency **This answer is correct.** 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 **This answer is correct.** privacy transparency A bank is developing a new artificial intelligence (AI) system to support the process of accepting or rejecting mortgage applications. Which two issues should be considered as part of the responsible AI principle of fairness to avoid biased decision making? Each correct answer presents part of the solution. Select all answers that apply. credit utilization **This answer is incorrect.** current salary ethnicity **This answer is correct.** gender **This answer is correct.** payment history **This answer is incorrect.** The AI system must be designed to ensure that biased decision making is avoided and not based on factors such as ethnicity and gender. The system will consider salary, payment history, and credit utilization. These are standard metrics. 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 **This answer is correct.** fairness inclusiveness **This answer is incorrect.** privacy and security **This answer is correct.** A company is currently developing driverless agriculture vehicles to help harvest crops. The vehicles will be deployed alongside people working in the crop fields, and as such, the company will need to carry out robust testing. Which principle of responsible artificial intelligence (AI) is most important in this case? Select only one answer. accountability Inclusiveness reliability and safety **This answer is correct.** transparency Which natural language processing (NLP) technique normalizes words before counting them? Select only one answer. frequency analysis N-grams stemming **This answer is correct.** vectorization **This answer is incorrect.** Stemming normalizes words before counting them. Frequency analysis counts how often a word appears in a text. N-grams extend frequency analysis to include multi-term phrases. Vectorization captures semantic relationships between words by assigning them to locations in n-dimensional space. 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? **Your Answer** - object detection **This answer is correct.** **Correct Answer** - object detection **This answer is correct.** Object detection provides the ability to generate bounding boxes identifying the locations of different types of vehicles in an image. The other answer choices also process images, but their outcomes are different. [Understand computer vision - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/4-understand-computer-vision) **Question 2 of 50** Which artificial intelligence (AI) workload scenario is an example of natural language processing (NLP)? **Your Answer** - predicting whether customers are likely to buy a product based on previous purchases **This answer is incorrect.** **Correct Answer** - extracting key phrases from a business insights report **This answer is correct.** Extracting key phrases from text to identify the main terms is an NLP workload. Predicting whether customers are likely to buy a product based on previous purchases requires the development of a machine learning model. Monitoring for sudden increases in quantity of failed sign-in attempts is a different workload. Identifying objects in landscape images is a computer vision workload. [Analyze text with the Language service - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-text-with-text-analytics-service/) **Question 3 of 50** Which two artificial intelligence (AI) workload scenarios are examples of natural language processing (NLP)? Each correct answer presents a complete solution. **Your Answer** - translating text between different languages from product reviews **This answer is correct.** **Correct Answer** - performing sentiment analysis on social media data **This answer is correct.** - translating text between different languages from product reviews **This answer is correct.** Translating text between different languages from product reviews is an NLP workload that uses the Azure AI Translator service and is part of Azure AI Services. It can provide text translation of supported languages in real time. Performing sentiment analysis on social media data is an NLP that uses the sentiment analysis feature of the Azure AI Service for Language. It can provide sentiment labels, such as negative, neutral, and positive for text-based sentences and documents. [Microsoft Azure AI Fundamentals: Explore natural language processing - Training \| Microsoft Learn](https://learn.microsoft.com/training/paths/explore-natural-language-processing/) **Question 4 of 50** Which two artificial intelligence (AI) workload features are part of the Azure AI Vision service? Each correct answer presents a complete solution. **Your Answer** - spatial analysis **This answer is correct.** **Correct Answer** - optical character recognition (OCR) **This answer is correct.** - spatial analysis **This answer is correct.** OCR and Spatial Analysis are part of the Azure AI Vision service. Sentiment analysis, entity recognition, and key phrase extraction are not part of the computer vision service. [Microsoft Azure AI Fundamentals: Explore computer vision -- Training \| Microsoft Learn](https://learn.microsoft.com/training/paths/explore-computer-vision-microsoft-azure/) **Question 5 of 50** Which principle of responsible artificial intelligence (AI) raises awareness about the limitations of AI-based solutions? **Your Answer** - transparency **This answer is correct.** **Correct Answer** - transparency **This answer is correct.** Transparency provides clarity regarding the purpose of AI solutions, the way they work, as well as their limitations. The privacy and security, reliability and safety, and accountability principles focus on the capabilities of AI, rather than raising awareness about its limitations. [Understand Responsible AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/8-understand-responsible-ai) [Identify principles and practices for responsible AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/paths/responsible-ai-business-principles/) **Question 6 of 50** 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? **Your Answer** - reliability and safety **This answer is incorrect.** **Correct Answer** - inclusiveness **This answer is correct.** The inclusiveness principle is meant to ensure that AI solutions empower and engage everyone, regardless of criteria such as physical ability, gender, sexual orientation, or ethnicity. Privacy and security, reliability and safety, and accountability do not discriminate based on these criteria, but also do not emphasize the significance of bringing benefits to all parts of the society. [Understand Responsible AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/8-understand-responsible-ai) **Question 7 of 50** Which principle of responsible artificial intelligence (AI) involves evaluating and mitigating the bias introduced by the features of a model? **Your Answer** - transparency **This answer is incorrect.** **Correct Answer** - fairness **This answer is correct.** Fairness involves evaluating and mitigating the bias introduced by the features of a model. Privacy is meant to ensure that privacy provisions are included in AI solutions. Transparency provides clarity regarding the purpose of AI solutions, the way they work, as well as their limitations. Accountability is focused on ensuring that AI solutions meet ethical and legal standards that are clearly defined. [Understand Responsible AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/8-understand-responsible-ai) **Question 8 of 50** Which principle of responsible artificial intelligence (AI) defines the framework of governance and organization principles that meet ethical and legal standards of AI solutions? **Your Answer** - transparency **This answer is incorrect.** **Correct Answer** - accountability **This answer is correct.** Accountability defines the framework of governance and organizational principles, which are meant to ensure that AI solutions meet ethical and legal standards that are clearly defined. The other answer choices do not define the framework of governance and organization principles, but provide guidance regarding the ethical and legal aspects of the corresponding standards. [Understand Responsible AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/8-understand-responsible-ai) **Question 9 of 50** Which principle of responsible artificial intelligence (AI) plays the primary role when implementing an AI solution that meet qualifications for business loan approvals? **Your Answer** - safety **This answer is incorrect.** **Correct Answer** - fairness **This answer is correct.** Fairness is meant to ensure that AI models do not unintentionally incorporate a bias based on criteria such as gender or ethnicity. Transparency does not apply in this case since banks commonly use their proprietary models when processing loan approvals. Inclusiveness is also out of scope since not everyone is qualified for a loan. Safety is not a primary consideration since there is no direct threat to human life or health in this case. [Understand Responsible AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/8-understand-responsible-ai) **Question 10 of 50** Which principle of responsible artificial intelligence (AI) ensures that an AI system meets any legal and ethical standards it must abide by? **Your Answer** - privacy and security **This answer is incorrect.** **Correct Answer** - accountability **This answer is correct.** The accountability principle ensures that AI systems are designed to meet any ethical and legal standards that are applicable. The privacy and security principle states that AI systems must be designed to protect any personal and/or sensitive data. The inclusiveness principle states that AI systems must empower people in a positive and engaging way. The fairness principle is applied to AI system to ensure that users of the systems are treated fairly. [Microsoft Azure AI Fundamentals: Explore computer vision - Training \| Microsoft Learn](https://learn.microsoft.com/training/paths/explore-computer-vision-microsoft-azure/) [Understand Responsible AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/8-understand-responsible-ai) **Question 11 of 50** Which type of machine learning algorithm groups observations is based on the similarities of features? **Your Answer** - supervised **This answer is incorrect.** **Correct Answer** - clustering **This answer is correct.** Clustering algorithms group data points that have similar characteristics. Regression algorithms are used to predict numeric values. Classification algorithms are used to predict a predefined category to which an input value belongs. Supervised learning is a category of learning algorithms that includes regression and classification, but not clustering. [Fundamentals of machine learning - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/) [What are classification models? - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/understand-classification-machine-learning/2-what-is-classification) [What is clustering? - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/train-evaluate-cluster-models/2-what-is-clustering) **Question 12 of 50** Which type of machine learning algorithm finds the optimal way to split a dataset into groups without relying on training and validating label predictions? **Your Answer** - supervised **This answer is incorrect.** **Correct Answer** - clustering **This answer is correct.** A clustering algorithm is an example of unsupervised learning, which groups data points that have similar characteristics without relying on training and validating label predictions. Supervised learning is a category of learning algorithms that includes regression and classification, but not clustering. Classification and regression algorithms are examples of supervised machine learning. [Fundamentals of machine learning - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/) [What are classification models? - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/understand-classification-machine-learning/2-what-is-classification) [What is clustering? - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/train-evaluate-cluster-models/2-what-is-clustering) **Question 13 of 50** Predicting rainfall for a specific geographical location is an example of which type of machine learning? **Your Answer** - regression **This answer is correct.** **Correct Answer** - regression **This answer is correct.** Predicting rainfall is an example of regression machine learning, as it will predict a numeric value for future rainfall by using historical time-series rainfall data based on factors, such as seasons. Clustering is a machine learning type that analyzes unlabeled data to find similarities in the data. Featurization is not a machine learning type, but a collection of techniques, such as feature engineering, data-scaling, and normalization. Classification is used to predict categories of data. [Regression - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/4-regression) **Question 14 of 50** 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? **Your Answer** - data transformation **This answer is incorrect.** **Correct Answer** - classification **This answer is correct.** Classification is used to predict categories of data. It can predict which category or class an item of data belongs to. In this example, sentiment analysis can be carried out on the Twitter posts with a numeric value applied to the posts to identify and classify positive or negative sentiment. Clustering is a machine learning type that analyzes unlabeled data to find similarities in the data. Regression is a machine learning scenario that is used to predict numeric values. Data transformation is not a machine learning type. [Clustering - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/7-clustering) **Question 15 of 50** 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? **Your Answer** - featurization **This answer is incorrect.** **Correct Answer** - classification **This answer is correct.** Classification is used to predict categories of data. It can predict which category or class an item of data belongs to. In this example, a machine learning model trained by using classification with labeled data can be used to determine the type of bone fracture in a new scan that is not labeled already. Featurization is not a machine learning type. Regression is used to predict numeric values. Clustering analyzes unlabeled data to find similarities in the data. [Clustering - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/7-clustering) **Question 16 of 50** Which assumption of the multiple linear regression model should be satisfied to avoid misleading predictions? **Your Answer** - Labels are independent of each other. **This answer is incorrect.** **Correct Answer** - Features are independent of each other. **This answer is correct.** Multiple linear regression models the relationship between several features and a single label. The features must be independent of each other, otherwise, the model\'s predictions will be misleading. [Multiple linear regression and R-squared - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/understand-regression-machine-learning/4-multiple-linear-regression) **Question 17 of 50** 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? **Your Answer** - price of the house **This answer is correct.** **Correct Answer** - price of the house **This answer is correct.** The price of the house is the label you are attempting to predict through the machine learning model. This is typically done by using a regression model. Floor space size, number of bedrooms, and age of the house are all input variables for the model to help predict the house price label. [Fundamentals of machine learning - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/) **Question 18 of 50** A company wants to predict household water use based on the number of people in a house, the weather temperature, and the time of year. In terms of data labels and features, what is the label in this use case? **Your Answer** - weather temperature **This answer is incorrect.** **Correct Answer** - water use **This answer is correct.** Water use is the label value that you want to predict, also known as the independent variable. Number of people in the house, weather temperature, and time of year are features, and are values that are dependent on the label. Number of people in the house, weather temperature, and time of year can influence the water consumed in a household. [Fundamentals of machine learning - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/) **Question 19 of 50** What is the purpose of a validation dataset used for as part of the development of a machine learning model? **Your Answer** - summarizing the data **This answer is incorrect.** **Correct Answer** - evaluating the trained model **This answer is correct.** The validation dataset is a sample of data held back from a training dataset. It is then used to evaluate the performance of the trained model. Cleaning missing data is used to detect missing values and perform operations to fix the data or create new values. Feature engineering is part of preparing the dataset and related data transformation processes. Summarizing the data is used to provide summary statistics, such as the mean or count of distinct values in a column. [Regression - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/4-regression) **Question 20 of 50** You need to create an automated machine learning (automated ML) model. Which resource should you create first in Azure Machine Learning studio? **Your Answer** - an Azure Kubernetes Service (AKS) cluster **This answer is incorrect.** **Correct Answer** - a dataset **This answer is correct.** A dataset is required to create an automated machine learning (automated ML) run. A workspace must be created before you can access Machine Learning studio. An Azure container instance and an AKS cluster can be created as a deployment target, after training of a model is complete. [Fundamentals of machine learning - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/) **Question 21 of 50** You need to use the Azure Machine Learning designer to deploy a predictive service from a newly trained model. What should you do first in the Machine Learning designer? **Your Answer** - Create an inferencing cluster. **This answer is incorrect.** **Correct Answer** - Create an inference pipeline. **This answer is correct.** To deploy a predictive service from a newly trained model by using the Machine Learning designer, you must first create a pipeline in the Machine Learning designer. Adding training modules by using the Machine Learning designer takes place before creating a trained model, which already exists. Adding a dataset by using the Machine Learning designer requires that a pipeline already exists. To create an inferencing cluster, you must use Machine Learning studio. [Regression - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/4-regression) **Question 22 of 50** Which machine learning algorithm module in the Azure Machine Learning designer is used to train a model? **Your Answer** - Select Columns in Dataset **This answer is incorrect.** **Correct Answer** - Linear Regression **This answer is correct.** Linear regression is a machine learning algorithm module used for training regression models. The Clean Missing Data module is part of preparing the data and data transformation process. Select Columns in Dataset is a data transformation component that is used to choose a subset of columns of interest from a dataset. Evaluate model is a component used to measure the accuracy of trained models. [Regression - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-machine-learning/4-regression) **Question 23 of 50** Which artificial intelligence (AI) technique should be used to extract the name of a store from a photograph displaying the store front? **Your Answer** - semantic segmentation **This answer is incorrect.** **Correct Answer** - optical character recognition (OCR) **This answer is correct.** OCR provides the ability to detect and read text in images. NLP is an area of AI that deals with identifying the meaning of a written or spoken language, but not detecting or reading text in images. Image classification classifies images based on their contents. Semantic segmentation provides the ability to classify individual pixels in an image. [Understand computer vision - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/4-understand-computer-vision) **Question 24 of 50** Which computer vision service provides bounding coordinates as part of its output? **Your Answer** - semantic segmentation **This answer is incorrect.** **Correct Answer** - object detection **This answer is correct.** Object detection provides the ability to generate bounding boxes that identify the locations of different types of objects in an image, including the bounding box coordinates, designating the location of the object in the image. Semantic segmentation provides the ability to classify individual pixels in an image. Image classification classifies images based on their contents. Image analysis extracts information from the image to label it with tags or captions. [Get started with image analysis on Azure - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-images-computer-vision/2-image-analysis-azure) [Understand computer vision - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/get-started-ai-fundamentals/4-understand-computer-vision) **Question 25 of 50** Which process allows you to use optical character recognition (OCR)? **Your Answer** - translating speech to text **This answer is incorrect.** **Correct Answer** - digitizing medical records **This answer is correct.** OCR can extract printed or handwritten text from images. In this case, it can be used to extract text from scanned medical records to produce a digital archive from paper-based documents. Identifying wildlife in an image is an example of a computer vision solution that uses object detection and is not suitable for OCR. Identifying a user requesting access to a laptop is done by taking images from the laptop's webcam and using facial detection and recognition to identify the user requesting access. Translating speech to text is an example of using speech translation and uses the Azure AI Speech service as part of Azure AI Services. [Read text with the Computer Vision service - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/read-text-computer-vision/) **Question 26 of 50** Which process allows you to use object detection? **Your Answer** - tracking livestock in a field **This answer is correct.** **Correct Answer** - tracking livestock in a field **This answer is correct.** Object detection can be used to track livestock animals, such as cows, to support their safety and welfare. For example, a farmer can track whether a particular animal has not been mobile. Sentiment analysis is used to return a numeric value based on the analysis of a text. Employee access to a secure building can be achieved by using facial recognition. Extracting text from manuscripts is an example of a computer vision solution that uses optical character recognition (OCR). [Machine learning for computer vision - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-images-computer-vision/2b-computer-vision-models) **Question 27 of 50** You have a set of images. Each image shows multiple vehicles. What allows you to identity different vehicle types in the same traffic monitoring image? **Your Answer** - optical character recognition (OCR) **This answer is incorrect.** **Correct Answer** - object detection **This answer is correct.** Object detection can be used to evaluate traffic monitoring images to quickly classify specific vehicle types, such as car, bus, or cyclist. Linear regression is a machine learning training algorithm for training regression models. Image classification is part of computer vision that is concerned with the primary contents of an image. OCR is used to extract text and handwriting from images. [Machine learning for computer vision - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-images-computer-vision/2b-computer-vision-models) **Question 28 of 50** Which feature of computer vision involves associating an image with metadata that summarizes the attributes of the image? **Your Answer** - tagging **This answer is correct.** **Correct Answer** - tagging **This answer is correct.** Tagging involves associating an image with metadata that summarizes the attributes of the image. Detecting image types involves identifying clip art images or line drawings. Content organization involves identifying people or objects in photos and organizing them based on the identification. Categorizing involves associating the contents of an image with a limited set of categories. [Get started with image analysis on Azure - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-images-computer-vision/2-image-analysis-azure) **Question 29 of 50** 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. **Your Answer** - inferencing **This answer is incorrect.** **Correct Answer** - choosing a model **This answer is correct.** - evaluating a model **This answer is correct.** - training a model **This answer is correct.** The computer vision service eliminates the need for choosing, training, and evaluating a model by providing pre-trained models. To use computer vision, you must create an Azure resource. The use of computer vision involves inferencing. [Machine learning for computer vision - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-images-computer-vision/2b-computer-vision-models) **Question 30 of 50** Which two specialized domain models are supported by using the Azure AI Vision service? Each correct answer presents a complete solution. **Your Answer** - landmarks **This answer is correct.** **Correct Answer** - celebrities **This answer is correct.** - landmarks **This answer is correct.** The Azure AI Vision service supports the celebrities and landmarks specialized domain models. It does not support specialized domain models for animals, cars, or plants. [Get started with image analysis on Azure - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-images-computer-vision/2-image-analysis-azure) **Question 31 of 50** Which additional piece of information is included with each phrase returned by an image description task of the Azure AI Vision? **Your Answer** - key **This answer is incorrect.** **Correct Answer** - confidence score **This answer is correct.** Each phrase returned by an image description task of the Azure AI Vision includes the confidence score. An endpoint and a key must be provided to access the Azure AI Vision service. Bounding box coordinates are returned by services such as object detection, but not image description. [Get started with image analysis on Azure - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-images-computer-vision/2-image-analysis-azure) **Question 32 of 50** When using the Face Detect API of the Azure AI Face service, which feature helps identify whether a human face has glasses or headwear? **Your Answer** - face rectangle **This answer is incorrect.** **Correct Answer** - face attributes **This answer is correct.** Face attributes are a set of features that can be detected by the Face Detect API. Attributes such as accessories (glasses, mask, headwear etc.) can be detected. Face rectangle, face ID, and face landmarks do not allow you to determine whether a person is wearing glasses or headwear. [What is the Azure Face service? - Azure Cognitive Services \| Microsoft Learn](https://learn.microsoft.com/azure/cognitive-services/computer-vision/overview-identity) [Detect and analyze faces with the Face service - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/detect-analyze-faces/) **Question 33 of 50** What is the confidence score returned by the Azure AI Language detection service of natural language processing (NLP) for an unknown language name? **Your Answer** - NaN **This answer is correct.** **Correct Answer** - NaN **This answer is correct.** NaN, or not a number, designates an unknown confidence score. Unknown is a value with which the NaN confidence score is associated. The score values range between 0 and 1, with 0 designating the lowest confidence score and 1 designating the highest confidence score. [Get started with text analysis - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-text-with-text-analytics-service/2-get-started-azure) **Question 34 of 50** Which part of speech synthesis in natural language processing (NLP) involves breaking text into individual words such that each word can be assigned phonetic sounds? **Your Answer** - tokenization **This answer is correct.** **Correct Answer** - tokenization **This answer is correct.** Tokenization is part of speech synthesis that involves breaking text into individual words such that each word can be assigned phonetic sounds. Transcribing is part of speech recognition, which involves converting speech into a text representation. Key phrase extraction is part of language processing, not speech synthesis. Lemmatization, also known as stemming, is part of language processing, not speech synthesis. [Recognize and synthesize speech - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/recognize-synthesize-speech/) **Question 35 of 50** 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? **Your Answer** - sentiment analysis **This answer is correct.** **Correct Answer** - sentiment analysis **This answer is correct.** Sentiment analysis provides sentiment labels, such as negative, neutral, and positive, based on a confidence score from text analysis. This makes it suitable for understanding user sentiment for product reviews. The named entity recognition, key phrase extraction, and language detection features cannot perform sentiment analysis for product reviews. [Analyze text with the Language service - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-text-with-text-analytics-service/) [What is sentiment analysis and opinion mining in Azure Cognitive Service for Language? - Azure Cognitive Services \| Microsoft Learn](https://learn.microsoft.com/azure/cognitive-services/language-service/sentiment-opinion-mining/overview) **Question 36 of 50** 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. **Your Answer** - named entity recognition **This answer is correct.** **Correct Answer** - key phrase extraction **This answer is correct.** - named entity recognition **This answer is correct.** Key phrase extraction is used to extract key phrases to identify the main concepts in a text. It enables a company to identify the main talking points from the support question data and allows them to identify common issues. Named entity recognition can identify and categorize entities in unstructured text, such as people, places, organizations, and quantities. The Azure AI Speech service, Conversational Language Understanding, and Azure AI Bot Service are not designed for identifying key phrases or entities. [Key Phrase Extraction cognitive skill -- Azure Cognitive Search \| Microsoft Learn](https://learn.microsoft.com/azure/search/cognitive-search-skill-keyphrases) [Extract insights from text with the Language service -- Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/extract-insights-text-with-text-analytics-service/) [Analyze text with the Language service -- Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-text-with-text-analytics-service/) **Question 37 of 50** 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? **Your Answer** - Personally Identifiable Information (PII) detection **This answer is incorrect.** **Correct Answer** - named entity recognition **This answer is correct.** Named entity recognition can identify and categorize entities in unstructured text, such as people, places, organizations, and quantities, and is suitable to support the development of an article recommendation system. Key phrase extraction, Content Moderator, and the PII feature are not suited to entity recognition tasks to build a recommender system. [What is the Named Entity Recognition (NER) feature in Azure Cognitive Service for Language? -- Azure Cognitive Services \| Microsoft Learn](https://learn.microsoft.com/azure/cognitive-services/language-service/named-entity-recognition/overview) [Analyze text with the Language service -- Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-text-with-text-analytics-service/) **Question 38 of 50** Which three values are returned by the language detection feature of the Azure AI Language service in Azure? **Your Answer** - Wikipedia URL **This answer is incorrect.** **Correct Answer** - ISO 6391 Code **This answer is correct.** - Language Name **This answer is correct.** - Score **This answer is correct.** Language Name, ISO 6391 Code, and Score are three values returned by the Language service of natural language processing (NLP) in Azure. Bounding box coordinates are returned by the Azure AI Vision services in Azure. Wikipedia URL is one of potential values returned by entity linking of entity recognition. [Get started with text analysis - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-text-with-text-analytics-service/2-get-started-azure) **Question 39 of 50** Which feature of the Azure AI Language service includes functionality that returns links to external websites to disambiguate terms identified in a text? **Your Answer** - sentiment analysis **This answer is incorrect.** **Correct Answer** - entity recognition **This answer is correct.** Entity recognition includes the entity linking functionality that returns links to external websites to disambiguate terms (entities) identified in a text. Key phrase extraction evaluates the text of a document and identifies its main talking points. Azure AI Language detection identifies the language in which text is written. Sentiment analysis evaluates text and returns sentiment scores and labels for each sentence. [Get started with text analysis - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/analyze-text-with-text-analytics-service/2-get-started-azure) **Question 40 of 50** Which type of translation does the Azure AI Translator service support? **Your Answer** - text-to-text **This answer is correct.** **Correct Answer** - text-to-text **This answer is correct.** The Azure AI Translator service supports text-to-text translation, but it does not support speech-to-text, text-to-speech, or speech-to-speech translation. [Get started with translation in Azure - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/translate-text-with-translation-service/2-get-started-azure) **Question 41 of 50** Which feature of the Azure AI Translator service is available only to Custom Translator? **Your Answer** - text translation **This answer is incorrect.** **Correct Answer** - model training with a dictionary **This answer is correct.** Model training with a dictionary can be used with Custom Translator when you do not have enough parallel sentences to meet the 10,000 minimum requirements. The resulting model will typically complete training much faster than with full training and will use the baseline models for translation along with the dictionaries you have added. [What is Custom Translator? - Azure Cognitive Services \| Microsoft Learn](https://learn.microsoft.com/azure/cognitive-services/translator/custom-translator/overview) [Introduction to Translator - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/intro-to-translator/) **Question 42 of 50** Which three sources can be used to generate questions and answers for a knowledge base? Each correct answer presents a complete solution. **Your Answer** - an existing FAQ document **This answer is correct.** **Correct Answer** - a webpage **This answer is correct.** - an existing FAQ document **This answer is correct.** - manually entered data **This answer is correct.** A webpage or an existing document, such as a text file containing question and answer pairs, can be used to generate a knowledge base. You can also manually enter the knowledge base question-and-answer pairs. You cannot directly use an image or an audio file to import a knowledge base. [Build a bot with the Language Service and Azure Bot Service - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/build-faq-chatbot-qna-maker-azure-bot-service/) **Question 43 of 50** 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. **Your Answer** - RESTful API services **This answer is incorrect.** **Correct Answer** - Copilots **This answer is correct.** Copilots are often integrated into applications to provide a way for users to get help with common tasks from a generative AI model. Copilots are based on a common architecture, so developers can build custom copilots for various business-specific applications and services. [What are copilots? - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-generative-ai/5-copilots) **Question 44 of 50** At which layer can you apply content filters to suppress prompts and responses for a responsible generative AI solution? **Your Answer** - user experience **This answer is incorrect.** **Correct Answer** - safety system **This answer is correct.** The safety system layer includes platform-level configurations and capabilities that help mitigate harm. For example, the Azure OpenAI service includes support for content filters that apply criteria to suppress prompts and responses based on the classification of content into four severity levels (safe, low, medium, and high) for four categories of potential harm (hate, sexual, violence, and self-harm). [Responsible generative AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/responsible-ai-studio/) **Question 45 of 50** 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. **Your Answer** - Deep learning **This answer is incorrect.** **Correct Answer** - Generative AI **This answer is correct.** Generative AI models offer the capability of generating images based on a prompt by using DALL-E models, such as generating images from natural language. The other AI capabilities are used in different contexts to achieve other goals. [What is generative AI? - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-generative-ai/2-what-is-generative-ai) **Question 46 of 50** As per the NIST AI Risk Management Framework, what is the first stage to consider when developing a responsible generative AI solution? **Your Answer** - Operate the solution. **This answer is incorrect.** **Correct Answer** - Identify potential harms. **This answer is correct.** Identifying potential harms is the first stage when planning a responsible generative AI solution. [Responsible generative AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/responsible-ai-studio/) **Question 47 of 50** Which two capabilities are examples of a GPT model? Each correct answer presents a complete solution. **Your Answer** - Understand natural language. **This answer is correct.** **Correct Answer** - Create natural language. **This answer is correct.** - Understand natural language. **This answer is correct.** Azure OpenAI natural language models can take in natural language and generate responses. GPT models are excellent at both understanding and creating natural language. [What is generative AI? - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-generative-ai/2-what-is-generative-ai) **Question 48 of 50** Which three capabilities are examples of image generation features for a generative AI model? Each correct answer presents a complete solution. **Your Answer** - new image creation **This answer is correct.** **Correct Answer** - creating variations of an image **This answer is correct.** - editing an image **This answer is correct.** - new image creation **This answer is correct.** Image generation models can take a prompt, a base image, or both, and create something new. These generative AI models can create both realistic and artistic images, change the layout or style of an image, and create variations of a provided image. [Fundamentals of Generative AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-generative-ai/) **Question 49 of 50** 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? **Your Answer** - image variations **This answer is incorrect.** **Correct Answer** - image description **This answer is correct.** Image description is not a capability included in the DALL-E model, therefore, it is not a use case that can be implemented by using DALL-E, while the other three capabilities are offered by DALL-E in Azure OpenAI. [Fundamentals of Generative AI - Training \| Microsoft Learn](https://learn.microsoft.com/training/modules/fundamentals-generative-ai/) **Question 50 of 50** Select the answer that correctly completes the sentence. **\[Answer choice\]** can search, classify, and compare sources of text for similarity. **Your Answer** - System messages **This answer is incorrect.** **Correct Answer** - Embeddings **This answer is correct.**