Download Exam AI-900 Microsoft Azure AI Fundamentals and more Exams Advanced Education in PDF only on Docsity!
Exam AI-900 Microsoft Azure AI Fundamentals
Which type of service provides a platform for conversational artificial intelligence (AI)? - Bot Services Which type of artificial intelligence (AI) workload has the primary purpose of making large amounts of data searchable? - Knowledge mining Which artificial intelligence (AI) workload scenario is an example of anomaly detection? - Monitoring the flow speed and low/high points of river water levels (Tips: Anomaly Detector service to detect abnormalities in time-series data.) Which artificial intelligence (AI) workload scenario is an example of natural language processing (NLP)? - Extracting key phrases from a business insights report For which scenario should you use anomaly detection? - detecting credit card fraud 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? - Inclusiveness Which principle of responsible artificial intelligence (AI) defines the framework of governance and organization principles that meet ethical and legal standards of AI solutions? - Accountability (Tip: 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.) Which principle of responsible artificial intelligence (AI) plays the primary role when implementing an AI solution that meet qualifications for business loan approvals? - Fairness (Tip: Fairness is meant to ensure that AI models do not unintentionally incorporate a bias based on criteria such as gender or ethnicity)
Which principle of responsible artificial intelligence (AI) is applied in the design of an AI system to ensure that users understand constraints and limitations of AI? - Transparency (Tip: The transparency principle states that AI systems must be designed in such a way that users are made fully aware of the purpose of the systems, how they work, and which limitations can be expected during use.) 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. - 1. Accountability
- Privacy and Security 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? - Reliability and safety Which type machine learning algorithm predicts a numeric label associated with an item based on that item's features? - Regression Which type of machine learning algorithm assigns items to a set of predefined categories? - Classification Which type of machine learning algorithm finds the optimal way to split a dataset into groups without relying on training and validating label predictions? - Clustering Predicting rainfall for a specific geographical location is an example of which type of machine learning? - Regression 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.
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? - Add a dataset THERE MIGHT BE AN ERROR IN THE PRACTICE TEST. (Tip: Before you can start training a machine learning model, you must first create a pipeline in the Machine Learning designer. This is followed by adding a dataset, adding training modules, and eventually deploying a service.) 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? - Create an inference pipeline (Tip: 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.) 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. - 1. Classification
- Regression
- Time-series forecasting Which machine learning algorithm module in the Azure Machine Learning designer is used to train a model? - Linear regression Which artificial intelligence (AI) technique should be used to extract the name of a store from a photograph displaying the store front? - Optical character recognition (OCR)
Which computer vision solution provides the ability to identify a person's age based on a photograph? - Facial detection Which two specialized domain models are supported by computer vision when categorizing an image? Each correct answer presents a complete solution. - 1. Celebrities
- Landmarks Which computer vision service provides bounding coordinates as part of its output? - Object detection (Tip: 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.) What allows you to identify different types of bone fractures in X-ray images? - Image classification Which analytical task of the computer vision service returns bounding box coordinates? - Object detection Which two specialized domain models are supported by using the computer vision service? Each correct answer presents a complete solution. - 1. Celebrities
- Landmarks Which additional piece of information is included with each phrase returned by an image description task of the computer vision service? - Confidence score When using the Face Detect API of the Face service, which feature helps identify whether a human face has glasses or headwear? - Face attributes When using the Face service, what should you use to perform one-to-many or one-to-one face matching? Each correct answer presents a complete solution. - 1. Face identification
- Face verification
What are the two main schema components of a Language Understanding app model? Each correct answer presents part of the solution. - 1. Entities
- Intents What is used to test a Language Understanding app model? - An utterance What are two main components of a conversational artificial intelligence (AI) solution? Each correct answer presents part of the solution. - 1. a bot service
- a knowledge base Which tool provides the easiest way to create a knowledge base for Azure Bot Service? - The Language Studio What are two required services to build a conversational artificial intelligence (AI) solution in Azure? Each correct answer presents part of the solution. - 1. Bot service
- Language Which two types of files can be imported to generate a knowledge base for use with Azure Bot Service? Each correct answer presents a complete solution. - 1. DOC
- PDF Which two capabilities are supported natively by Azure Bot Service? Each correct answer presents a complete solution. - 1. responding to email questions
- responding to new student FAQs Which three sources can be used to generate questions and answers for a knowledge base? Each correct answer presents a complete solution. - 1. a webpage
- an existing FAQ document
- manually entered data Which bot communication channel requires an application to be registered with the channel? - Facebook
Which artificial intelligence (AI) technique serves as the foundation for modern image classification solutions? - Deep Learning Which process allows you to use optical character recognition (OCR)? - Digitizing medical records What allows you to identify different vehicle types in traffic monitoring images? - Object detection (Tip: Object detection can be used to evaluate traffic monitoring images to quickly classify specific vehicle types, such as car, bus, or cyclist. Image classification is part of computer vision that is concerned with the primary contents of an image..) What can be used for an attendance system that can scan handwritten signatures? - Optical Character Recognition (OCR) Which feature of computer vision involves associating an image with metadata that summarizes the attributes of the image? - Tagging Which two Form Recognizer models include identifying common data fields as part of its data extraction capabilities? Each correct answer presents a complete solution. - 1. Business Card Model
- Invoice Model Which service can you use to train an image classification model? - Custom Vision (Tip: Custom Vision is an image recognition service that allows you to build and deploy your own image models. The computer vision service, Face service, and Language service do not provide the capability to train your own image model.) 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? - Classification
Which feature of the Translator service is available only to Custom Translator? - Model training with a dictionary (Tip: 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.) When using the Azure Cognitive Service for Language, what should you use to provide further information online about entities extracted from a text? - Entity linking What are two required services to build a conversational artificial intelligence (AI) solution in Azure? Each correct answer presents part of the solution. - Which process allows you to use object detection? A. Analyzing sentiment around news articles B. Extracting text from manuscripts C. Granting employee access to a secure building D. Tracking livestock in a field - D. Tracking livestock in a field What can be used for an attendance system that can scan handwritten signatures? - Optical character recognition (OCR) Which three parts of the machine learning process does the computer vision service eliminate the need for? Each correct answer presents part of the solution. - 1. Choosing a model
- Evaluating a model
- Training a model In a regression machine learning algorithm, what are the characteristics of features and labels in a training dataset? - Known features and label values
In a regression machine learning algorithm, what are the characteristics of features and labels in a validation dataset? - Known features and label values Tip: In a regression machine learning algorithm, a validation set contains known feature and label values. What is an unsupervised machine learning algorithm module for training models in the Azure Machine Learning designer? - K-Means Clustering Which two artificial intelligence (AI) workload scenarios are examples of natural language processing (NLP)? Each correct answer presents a complete solution. - 1. performing sentiment analysis for social media data
- translating text between different languages from product reviews 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. - 1. Ethnicity
- Gender You are exploring solutions to improve the document search and indexing service for employees. You need an artificial intelligence (AI) search solution that will include searching text in various types of documents, such as images. Which type of AI workload is this? - Data mining What is the first step in the statistical analysis of terms in a text in the context of natural language processing (NLP)? - Removing stop words Tip:
- Encoding words as numeric features is not part of statistical analysis - it is frequently used in sentiment analysis
- Vectorized model is not part of statistical analysis - it is used to capture the semantic relationship between words
Tip: Clustering algorithms group data points that have similar characteristics. Classification is used to predict a predefined category to which an input value belongs. An electricity utility company wants to develop a mobile app for its customers to monitor their energy use and to display their predicted energy use for the next 12 months. The company wants to use machine learning to provide a reasonably accurate prediction of future energy use by using the customers' previous energy-use data. Which type of machine learning is this? - Regression Which feature makes regression an example of supervised machine learning? - use of historical data with known label values to train a model 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. - A. Weather B. Weekend or weekday What is the purpose of a validation dataset used for as part of the development of a machine learning model? - Evaluating the trained model What should you do after preparing a dataset and before training the machine learning model? - Split the data into training and validation datasets Tip: Splitting data into training and validation datasets leaves you with two datasets, the first and largest of which is the training dataset you use to train the model. The second, smaller dataset is the held back data and is called the validation dataset, as it is used to evaluate the trained model. If normalizing or summarizing the data is required, it will be carried out as part of data transformation. Cleaning missing data is part of preparing the data and the data transformation processes.
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? - Deploy the model to an endpoint. Tip: You can deploy the best performing model for client applications to use over the internet by using an endpoint. Compute clusters are used to train the model and are created directly after you create a Machine Learning workspace. Before you can test the model's endpoint, you must deploy it first to an endpoint. Automated ML performs the validation automatically, so you do not need to split the dataset. 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. - A. Classification B. Regression C. Time-series forecasting Which type of artificial intelligence (AI) workload relies on sensors to proactively detect an impending failure of electronic equipment? - anomaly detection Which type of artificial intelligence (AI) workload is used to monitor credit card transactions? - Which type of artificial intelligence (AI) workload is used to monitor credit card transactions? Which artificial intelligence (AI) workload scenario is an example of natural language processing (NLP)? - extracting key phrases from a business insights report Which principle of responsible artificial intelligence (AI) involves evaluating and mitigating the bias introduced by the features of a model? Select only one answer. - Fairness Tip: think of race / gender in loan approval predictions 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? - Sentiment analysis
What are two main components of a conversational artificial intelligence (AI) solution? Each correct answer presents part of the solution. - A. Bot service B. A knowledge base What are two required services to build a conversational artificial intelligence (AI) solution in Azure? Each correct answer presents part of the solution. - A. Bot Service B. Language service Tip: Knowledge base is part of the Language service Which two capabilities are supported natively by Azure AI Bot Service? Each correct answer presents a complete solution. - A. responding to email questions B. answering FAQs Which three sources can be used to generate questions and answers for a knowledge base? Each correct answer presents a complete solution. - Which artificial intelligence (AI) technique serves as the foundation for modern image classification solutions? - Deep learning Which type of artificial intelligence (AI) workload provides the ability to classify individual pixels in an image depending on the object that they represent? - Semantic Segmentation Tip: Semantic segmentation provides the ability to classify individual pixels in an image depending on the object that they represent. Image classification is used to determine the main subject of an image. Which two artificial intelligence (AI) workload features are part of the Azure AI Vision service? Each correct answer presents a complete solution. - A. optical character recognition (OCR) B. spatial analysis
Which two prebuilt models allow you to use the Azure AI Document Intelligence service to scan information from international passports and sales accounts? Each correct answer presents part of the solution. - A. Invoice model B. ID document model Which service can you use to train an image classification model? - Azure AI Custom Vision You need to use Azure Machine Learning to train a regression model. What should you create in Machine Learning studio? - A job You need to create an automated machine learning (automated ML) model. Which resource should you create first in Azure Machine Learning studio? - a dataset What are the 4 steps to responsible Generative AI solution? - 1. Identify potential harms
- Measure the presence and impact
- Mitigate harms
- Operate responsibly What are the main factors to consider when trying to identify harm? - 1. Specific services
- Model used
- Fine-tuning techniques
- Grounding data Common types of harm related to generative AI: - 1. Offensive or discriminatory harm
- Factual inaccuracies
- Content that encourages illegal or unethical practices List 4 steps in identifying harm (generative AI) - 1. Identify harms
- Prioritize harms based on: likelihood of occurrence and level of impact
What does the system layer of a generative AI solution involve? - Platform-level configurations and capabilities What's an example of a safety system layer configuration or capability? (generative AI) - Azure OpenAI's content filters What is a content filter? - Applies criteria to suppress prompts and responses based on classification of content into:
- 4 severity levels
- 4 categories of harm What are some mitigation techniques used at the safety system layer? - 1. Abuse detection algorithms
- Alert notifications What is the metaprompt and grounding layer? (generative AI) - Involves the construction of prompts submitted to the model What are some mitigation techniques you can use at the metaprompt and grounding layer? - 1. Specifying metaprompts or system inputs that define behavioral parameters
- Applying prompt engineering to add grounding data
- Retrieval augmented generation (RAG) to retrieve contextual data from trusted data sources and include it in prompts What is a Large Language Model (LLM)? - Specialized type of ML model that can be used to perform NLP tasks
What are some examples of NLP tasks that an LLM can perform? - 1. Determining sentiment or classifying NLP text
- Summarizing text
- Comparing text sources for semantic similarity
- Generating new natural language Transformer model architecture consists of two components, or blocks. What are they? - 1. Encoder block - creates semantic representations of training vocabulary
- A decoder block - generates new language sequences LLMs based on Transformer architecture have proven to be successful in _______ & _______. - 1. Modeling vocabularies
- Generating language What is the first step in training a transformer model? - Decompose training text into tokens What type of architecture are LLMs based on? - Transformer What is the first step in training a transformer model? - Tokenization What happens as you continue to train a transformer model? - Each new token in the training text is added to the vocabulary with appropriate token IDs Why define embeddings or contextual vectors? (transformer model) - To create a vocabulary that include semantic relationships between tokens
