AI-900 Questions

In Azure Machine Learning studio, what can you use to author regression machine learning pipelines using a drag-and-drop interface? a. Notebooks b. Automated machine learning c. Designer

c. Designer Correct. You can use Designer to author regression pipelines with a drag-and-drop interface.

What is the confidence score returned by the language detection service of natural language processing (NLP) for an unknown language name? a. -1 b. 1 c. NaN d. Unknown

c. NaN 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.

You have published an image classification model. What information must you provide to developers who want to use it? A. Only the project ID. B. The project ID, the model name, and the key and endpoint for the prediction resource Correct: To use a published model, you need the project ID, the model name, and the key and endpoint for the prediction resource. C. The project ID, iteration number, and the key and endpoint for the training resource. Incorrect: You need the model name rather than the iteration number; and the key and endpoint must be for the prediction resource, not the training resource.

B. The project ID, the model name, and the key and endpoint for the prediction resource Correct: To use a published model, you need the project ID, the model name, and the key and endpoint for the prediction resource. C. The project ID, iteration number, and the key and endpoint for the training resource. Incorrect: You need the model name rather than the iteration number; and the key and endpoint must be for the prediction resource, not the training resource.

Before you can start training a machine learning model what must you create first in Machine Learning designer?

a pipeline which is then followed by adding a dataset, training modules and deploying a service

What are the variables we are trying to predict in regression known as?

Labels

What are 3 potential uses for image classification?

Product identification: performing visual searches for specific products in online searches or even, in-store using a mobile device. Disaster investigation: identifying key infrastructure for major disaster preparation efforts. For example, identifying bridges and roads in aerial images can help disaster relief teams plan ahead in regions that are not well mapped. Medical diagnosis: evaluating images from X-ray or MRI devices could quickly classify specific issues found as cancerous tumors, or many other medical conditions related to medical imaging diagnosis.

What is an example of Regression?

Regression is an example of supervised machine learning due to the use of historical data with known label values to train a model. Regression does not reply on randomly generated data for training.

You use Azure Machine Learning designer to create a training pipeline for a classification model. What must you do before deploying the model as a service? a. Create an inference pipeline from the training pipeline b. Add an Evaluate Model module to the training pipeline c. Clone the training pipeline with a different name

a. Create an inference pipeline from the training pipeline Correct. You must create an inference pipeline to deploy as a service.

You plan to use the Custom Vision service to train an image classification model. You want to create a resource that can only be used for model training, and not for prediction. Which kind of resource should you create in your Azure subscription? a. Custom Vision b. Cognitive Services c. Computer Vision

a. Custom Vision Correct: When you create a Custom Vision resource, you can specify whether it is to be used for training, prediction, or both.

You would like to summarize a paragraph of text. Which generative AI model family would you use to solve for this workload? a. GPT b. Codex c. Dall-E

a. GPT

You want to use the Computer Vision service to identify the location of individual items in an image. Which of the following features should you retrieve? a. Objects b. Tags c. Categories

a. Objects Correct. Computer Vision returns objects with a bounding box to indicate their location in the image.

What is one action Microsoft takes to support ethical AI practices in Azure OpenAI? a. Provides Transparency Notes that share how technology is built and asks users to consider its implications. b. Logs users out of Azure OpenAI Studio after a period of inactivity to ensure it's only used by one user. c. Allows users to build any application, regardless of harmful effects, to ensure fairness.

a. Provides Transparency Notes that share how technology is built and asks users to consider its implications.

You plan to use the Computer Vision service's Read API. What results can the Read API provide? a. Results arranged in pages, lines, and words b. Only the bounding box coordinations c. Results arranged by pages that have photographs first, then pages that exclusively have text

a. Results arranged in pages, lines, and words Correct: The Read API takes an image and extracts the words, organizing the results by page and line.

You are using an Azure Machine Learning designer pipeline to train and test a K-Means clustering model. You want your model to assign items to one of three clusters. Which configuration property of the K-Means Clustering module should you set to accomplish this? a. Set Number of Centroids to 3 b. Set Random number seed to 3 c. Set Iterations to 3

a. Set Number of Centroids to 3 That is correct. To create K clusters, you must set the number of centroids to K

You want to use automated machine learning to train a regression model with the best possible R2 score. How should you configure the automated machine learning experiment? a. Set the Primary metric to R2 score b. Block all algorithms other than GradientBoosting c. Enable featurization

a. Set the Primary metric to R2 score Correct. The primary metric determines the metric used to evaluate the best performing model.

You use the Language service to perform sentiment analysis on a document, and a score of 0.99 is returned. What does this score indicate about the document sentiment? a. The document is positive. b. The document is neutral. c. The document is negative.

a. The document is positive. Correct. Score values closer to 1 indicated a more positive sentiment where scores closer to 0 indicated negative sentiment.

Which type machine learning algorith predicts a numeric label associated with an item based on that item's features? a. regression b. clustering c. classification d. unsupervised

a. regression

What is the first step in the statistical analysis of terms in a text in the context of natural language processing (NLP)? a. removing stop words b. counting the occurrences of each word c. creating a vectorized model d. encoding words as numeric features

a. removing stop words Removing stop words is the first step in the statistical analysis of terms used in a text in the context of NLP. Counting the occurrences of each word takes place after stop words are removed. Creating a vectorized model is not part of statistical analysis. It is used to capture the sematic relationship between words. Encoding words as numeric features is not part of statistical analysis. It is frequently used in sentiment analysis.

Which feature makes regression an example of supervised machine learning? a. use of historical data with known label values to train a model b. use of historical data with unknown label values to train a model c. use of randomly generated data with known label values to train a model d. use of randomly generated data with unknown label values to train a model

a. use of historical data with known label values to train a model

You are using the Form Recognizer service to analyze receipts that you have scanned into JPG format images. What is the maximum file size of JPG file you can submit to the pre-built receipt model? a. 2 MB b. 50 MB c. 200 MB

b. 50 MB Correct: The maximum file size for the pre-built receipt model is 50 MB

You use Azure Machine Learning designer to create a training pipeline for a clustering model. Now you want to use the model in an inference pipeline. Which module should you use to infer cluster predictions from the model? a. Score Model b. Assign Data to Clusters c. Train Clustering Model

b. Assign Data to Clusters That is correct. use the Assign Data to Clusters module to generate cluster predictions from a trained clustering model

You want to use the Computer Vision service to analyze images. You also want to use the Language service to analyze text. You want developers to require only one key and endpoint to access all of your services. What kind of resource should you create in your Azure subscription? a. Computer Vision b. Cognitive Services c. Custom Vision

b. Cognitive Services Correct. A Cognitive Services resource supports both Computer Vision and Language.

What is one aspect that may impair facial detection? a. Glasses b. Extreme angles c.Fast shutter speed

b. Extreme angles Correct: Best results are obtained when the faces are full-frontal or as near as possible to full-frontal

You plan to use the Form Recognizer pre-built receipt model. Which kind of Azure resource should you create? a. Computer Vision resource b. Form Recognizer or Cognitive Services resource c. Only Form Recognizer resource

b. Form Recognizer or Cognitive Services resource Correct: Both the Form Recognizer resource and Cognitive Services resource provide access to the Form Recognizer service

You want to use the Language service to determine the key talking points in a text document. Which feature of the service should you use? a. Sentiment analysis b. Key phrase extraction c. Entity detection

b. Key phrase extraction Correct. Key phrases can be used to identify the main talking points in a text document.

An automobile dealership wants to use historic car sales data to train a machine learning model. The model should predict the price of a pre-owned car based on its make, model, engine size, and mileage. What kind of machine learning model should the dealership use automated machine learning to create? a. Classification b. Regression c.

b. Regression Correct. To predict a category, or class, use a classification model.

A bank wants to use historic loan repayment records to categorize loan applications as low-risk or high-risk based on characteristics like the loan amount, the income of the borrower, and the loan period. What kind of machine learning model should the bank use automated machine learning to create? a. Classification b. Regression c. Time series forecasting

b. Regression Correct. To predict a numeric value, use a regression model.

You're using Azure Machine Learning designer to create a training pipeline for a binary classification model. You've added a dataset containing features and labels, a Two-Class Decision Forest module, and a Train Model module. You plan to use Score Model and Evaluate Model modules to test the trained model with a subset of the dataset that wasn't used for training. What's another module should you add? a. Join Data b. Split Data c. Select Columns in Dataset

b. Split Data Correct. Use a Split Data module to randomly split a dataset into training and validation subsets.

Why do you split data into training and validation sets? a. Data is split into two sets in order to create two models, one model with the training set and a different model with the validation set. b. Splitting data into two sets enables you to train the model with the training set and test the model on unseen data from the test set. c. Only split data when you use the Azure Machine Learning Designer, not in other machine learning scenarios.

b. Splitting data into two sets enables you to train the model with the training set and test the model on unseen data from the test set. Correct. When you test the model with unseen data from the test set, you can compare the model's predicted labels against the test set's labels.

You need to create an automated machine learning (automated ML) model. Which resource should you create first in Azure Machine Learning studio? a. workspace b. a dataset c. an azure container instance. d. an azure Kubernetes Service (AKS) cluster

b. a dataset

You want to extract text from images and then use the Language service to analyze the text. You want developers to require only one key and endpoint to access all of your services. What kind of resource should you create in your Azure subscription? a. computer vision b. cognitive services c. language

b. cognitive services Correct. A Cognitive Services resource supports both Computer Vision for text extraction, and Language for text analytics. a. computer vision Incorrect. This resource type only supports image analysis. A separate resource (with its own key and endpoint) would be required for text analytics with the Language service.

You are creating a training pipeline for a regression model. You use a dataset that has multiple numeric columns in which the values are on different scales. You want to transform the numeric columns so that the values are all on a similar scale. You also want the transformation to scale relative to the minimum and maximum values in each column. Which module should you add to the pipeline? a. Select Columns in a Dataset b. Clean Missing Data c, Normalize Data

c, Normalize Data Correct. When you transform numeric data to be on a similar scale, use a Normalize Data module.

You plan to use Face to detect human faces in an image. How does the service indicate the location of the faces it detects? a. A pair of coordinates for each face, indicating the center of the face b. Two pairs of coordinates for each face, indicating the location of the eyes c. A set of coordinates for each face, defining a rectangular bounding box around the face

c. A set of coordinates for each face, defining a rectangular bounding box around the face Correct: The locations of detected faces are indicated by coordinates for a rectangular bounding box

You train an image classification model that achieves less than satisfactory evaluation metrics. How might you improve it? a. Reduce the size of the images used to train the model. b. Add a new label for "unknown" classes. c. Add more images to the training set.

c. Add more images to the training set. Correct: Generally, adding more images to the project and retraining the model is likely to improve performance.

How are ChatGPT, OpenAI, and Azure OpenAI related? a. ChatGPT and OpenAI are chatbots that generate natural language, code, and images. Azure OpenAI provides access to these two chatbots. b. Azure OpenAI is Microsoft's version of ChatGPT, a chatbot that uses generative AI models. c. OpenAI is a research company that developed ChatGPT, a chatbot that uses generative AI models. Azure OpenAI provides access to many of OpenAI's AI models.

c. OpenAI is a research company that developed ChatGPT, a chatbot that uses generative AI models. Azure OpenAI provides access to many of OpenAI's AI models.

You want to use the Computer Vision service to analyze images of locations and identify well-known buildings. What should you do? a. Retrieve the objects in the image. b. Retrieve the categories for the image, specifying the celebrities domain c. Retrieve the categories for the image, specifying the landmarks domain

c. Retrieve the categories for the image, specifying the landmarks domain Correct. The landmarks domain includes many well-known buildings around the world.

You use an Azure Machine Learning designer pipeline to train and test a binary classification model. You review the model's performance metrics in an Evaluate Model module, and note that it has an AUC score of 0.3. What can you conclude about the model? a. The model can explain 30% of the variance between true and predicted labels. b. The model predicts accurately for 70% of test cases. c. The model performs worse than random guessing.

c. The model performs worse than random guessing. Correct. An AUC of 0.5 is what you'd expect with random prediction of a binary model.

When might you see NaN returned for a score in Language Detection? a. When the score calculated by the service is outside the range of 0 to 1 b. When the predominant language in the text is mixed with other languages c. When the language is ambiguous

c. When the language is ambiguous Correct. The service will return NaN when it cannot determine the language in the provided text.

Which natural language processing (NLP) technique assigns values to words such as plant and flower, so that they are considered closer to each other than a word such as airplane? a. frequency analysis b. N-grams c. lemmatization d. vectorization

d. vectorization Vectorization captures semantic relationships between words by assigning them to locations in n-dimensional space. Lemmatization, also known as 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.

Regression works by establishing a relationship between variables in the data that present characteristics, known as _______ ?

features (of the thing being observed)

What does image classification use in order to identify real-world items based on images?

predictive power of machine learning Image classification is a common workload in artificial intelligence (AI) applications. It harnesses the predictive power of machine learning to enable AI systems to identify real-world items based on images.

What does machine learning classification help predict?

which category, or class, something belongs to.