FREE Microsoft Azure AI Fundamentals General Questions and Answers
You're employed by a car dealership. Your employer requests that you give him forecast data. Will the new auto model succeed or fail? The new model sports a sunroof, improved seats, and many engine upgrades. You created a list of information about previous successful models, including details about their features and sales figures. What should you do to ensure the success of the new model during the pre-processing of the data stage?
You must work with the data to choose the features that affect label prediction during pre-processing. Features in this problem include things like seat comforts, engine power or volume, etc. They could support the ML model's ability to forecast the new automobile model's commercial viability. We may need to exclude the sunroof from the final collection of features we will use for model training because it may not be necessary to predict the label.
You are analyzing the line "After Peter met Sara at Microsoft's Paris office, they toured the Eiffel tower" using the Text Analytics Entity Recognition API. What proportion of entities under the category "Location" can you anticipate in the API response?
A Text Analytics service called Named Entity Recognition (NER) assists in locating and classifying entities in the text into categories like person, organization, location, event, etc. With the category "Location," the API response should contain the three well-known named entities "headquarters," "Paris," and "Eiffel tower."
An extensive dataset of brain scan images that have been anonymised and classified into different forms of brain hemorrhages is being used in a medical research study. Before the photos are analyzed by a person, machine learning must be used to help early detection of the many forms of brain hemorrhages in the images. Which kind of machine learning does this represent?
Classification is a type of supervised machine learning where the goal is to categorize data points into predefined classes or categories based on their features. In this case, the brain scan images are being categorized into different brain hemorrhage types, making it a classification task. The algorithm learns from the labeled examples in the dataset and then makes predictions on new, unseen images to determine which brain hemorrhage type they belong to.
What forms the core of the personal digital assistant?
The Bot Framework-based Personal Digital Assistant is a solution. There are three key parts to it: the Azure Bot Service, the Bot Framework, and the Knowledge Base.
You must use the Azure portal to create a Web Bot. You must select a bot template. Which two SDK dialects are available for the bot template?
Please select 2 correct answers
Only C# and Node.js templates are offered by the Azure Bot Framework SDK.
What markup language will you employ to manage the output of your phone's speech synthesizer?
Speech Synthesis output is controlled via the Speech Synthesis Markup Language (SSML) in Azure Cognitive services. You can control the voice's pitch and pace using SSML and XML-based language, as well as how the entire text or specific portions of it should be read.
For the production environment, you are constructing a compute cluster. You've limited the number of nodes to five. What number of nodes should be the bare minimum?
In the production environment, there should be zero nodes at the very least. A compute cluster will be automatically halted (deallocated) during an idle period and restarted when necessary with this configuration. It will cut expenses and energy use.
What platform offers a Conversation AI agent user interface?
For Conversation AI agents or bots, Azure Bot Service offers a user interface and links to the various channels.
What popular ML algorithm do you use when building a Clustering Model?
A machine learning technique called clustering groups objects based on a few shared characteristics. K-means Clustering is the most popular clustering algorithm.
What kind of methodology is the Face Recognition system built on?
The goal of applied method is to create "smart" systems that are commercially feasible, such as a security system that identifies faces to grant access. The used strategy has already had a lot of success.
Which of the following describes how artificial intelligence is advantageous?
Without human intervention, a machine can think and decide thanks to artificial intelligence.
Why should you randomly divide the rows into several subsets when training a model?
When training a model, you should randomly split the rows into separate subsets to test the model by using data that was not used to train the model. This process is commonly known as train-test splitting or cross-validation. The main reason for doing this is to evaluate the performance of the model on data it hasn't seen during training. By splitting the dataset into a training subset and a separate testing subset, you can assess how well the model generalizes to new, unseen data. This helps to determine whether the model has learned meaningful patterns or if it's simply memorizing the training data (overfitting).
Your company's customer care department spends a lot of time responding to the same queries. They requested your assistance in automating this process. You received a Microsoft Excel (*.xlsx) document from them that had common queries and usual responses. What service will you employ to turn this document into a knowledge base?
Use the QnA Maker service, please. The QnA Maker resource must first be provisioned in your Azure subscription. Following that, you can use the frequently asked questions (FAQ) document to populate the newly generated knowledge base.
Which of the following can help an AI agent perform better?
By preserving previous states, an AI agent can learn from them and react to similar situations more effectively in the future. Therefore, learning can help an AI agent perform better.
Choose every model that makes up Supervised ML.
A Supervised machine learning includes the modeling types for regression and classification. Both methodologies use labeled data—previously collected or historical data for the label—to train the algorithms.
For the following ten years, you must forecast the sea level in meters. Which kind of machine learning ought to be applied?
Regression is essentially the prediction of a numerical target. A linear relationship between one or more independent variables and a numerical result, or dependent variable, is sought after via linear regression. This module is used to specify a linear regression technique, after which a model is trained using a labeled dataset. Predictions can then be made using the trained model.