FREE Microsoft Azure AI Fundamentals MCQ Questions and Answers
The idea that everyone in society, regardless of gender or race, should benefit from ethical AI systems is known as: .
Responsible AI systems should engage and empower everyone. Regardless of physical ability, gender, sexual orientation, race, or other variables ensuring inclusion, AI should help all facets of society.
What method is the foundation for current picture categorization solutions?
Convolutional neural networks (CNNs) are used in contemporary image classification approaches to discover patterns in the pixels that make up a picture and map them to a certain class. An artificial intelligence approach called anomaly detection looks for out-of-the-ordinary occurrences in data patterns. Instead of being classifications, both linear and multiple linear regression are regression procedures.
By using ________________, you can swap chatbot activity with other services.
Activities are shared via many channels, including email, web chat, and Microsoft Teams. Cards are decorative objects that convey messages. A flow of actions creates dialog. Turn-by-turn completion of tasks results in a user contact with a chatbot.
Based on the dogs' age and body fat percentage, you want to utilize machine learning to estimate how sick the dogs will become. The model has to have .
You are attempting to construct a correlation between two characteristics (a dog's age and body fat %) and one label in the current situation, which serves as a model (the likelihood of that dog becoming ill).
You prepare an Azure Machine Learning model for deployment as a predictive service in a real-world setting. Before deploying the model to _______________, an inference cluster needs to be created.
You can choose to deploy a predictive service to Azure Container Instance (ACI) or Azure Kubernetes Service in Azure Machine Learning (AKS). Use an AKS deployment, which necessitates constructing an inference cluster compute target, for production scenarios. Testing can be done using deployments based on ACI. Predictive services cannot be deployed to Azure Functions or Azure Logic Apps using Azure Machine Learning.
You want to use Azure Machine Learning's AutoML UI to create and deploy a predictive model. What are the three supported machine learning tasks?
Please select 3 correct answers
Machine learning tasks for categorization, regression, and forecasting are supported by AutoML UI. On theย clustering and reinforcement learning are not supported.
Using _____________________, you may extract the information from food product labels.
OCR enables the extraction of printed text. Because image classification cannot recognize words on an object, it is a distraction. The method of handling linguistic data known as "natural language processing" is distracting. Since it is used to divide up specific portions of an image, image segmentation is incorrect.
To find brand logos in photos, you must train a machine learning model. Which should you employ?
Azure Custom Vision's object detection feature can recognize logos in photos. A set of photos is categorized into groups using Azure Custom Vision's image classification capabilities. For the purpose of recognizing faces, Azure Face Service is employed. The service is unable to recognize logos. LUIS is employed to comprehend natural language.
What are the Azure Computer Vision service's two features?
Please select 2 correct answers
An Azure resource called Azure Computer Vision provides training and forecasting capabilities. It does not let you examine and visualize datasets, nor does it let you author models.
Based on their voice, users must be recognized. Which feature of the Azure Speech service should you employ?
Algorithms are provided by the Speaker Recognition service to check and distinguish speakers based on their distinctive voice characteristics. To create transcripts of a discussion, use the Conversation transcription service. Evaluation of pronunciation measures the precision and fluidity of spoken audio. Because LUIS is used to interpret natural language, which cannot be utilized to distinguish speakers, it is a distraction.
Which kind of artificial intelligence workload employs sensors to foretell future equipment mechanical problems and inform users beforehand?
Analyzing historical data enables anomaly detection, which looks for odd occurrences like variations in engine speed or brake temperature. The situation referred to in the question does not involve conversational AI, computer vision, or natural language processing.
From a collection of PDF documents, you need to gather the names of individuals, groups, and occasions. Which natural language processing feature ought to be used?
A variety of prebuilt entities, including persons, locations, and organizations, can be used for entity identification in PDF documents thanks to the named entity recognition capability in text analytics.
The idea that responsible AI-based solutions have constraints is known as the _______________ principle.
Transparency makes it clear what AI solutions are used for, how they operate, and what their limitations are. Other ethical AI guidelines are intended to be applied to all AI solutions, despite their flaws.
Which of these attributes does the Azure Text Analytics service support?
The integration of chatbots, multilingual content, and confidence scoring are all supported by Azure Text Analytics. It can understand 120 different languages. documents must not exceed 5,120 characters in length.
You develop a model for multiclass classification. You must assess the model. Which two metrics for evaluation are available?
Please select 2 correct answers
The F1 score and accuracy measures can be used to assess classification methods. For classification evaluation, the F1 score combines precision and recall, whereas accuracy assesses the proportion of accurate predictions. Clustering model evaluation uses the Rand index. Regression model evaluation is done using MSE.
Determine numerical values that, given a dog's age and body fat percentage, indicate the likelihood that it will get sick. What kind of machine learning model need to you employ?
The main distinction between multiple linear regression and linear regression, which employs a single feature, is that multiple linear regression models relationships between many features and a single label. A classification model is a logistic regression, and a clustering approach is a hierarchical clustering.