AI-900 Exam
Which of the following are one of the Azure Cognitive Services six principles of responsible AI? (Choose 2 answers) a) Transparency b) Fairness c) Communication d) Collaboration
a) Transparency b) Fairness
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
a) Classification
You have been given a data set that is unlabeled and includes detailed customer information. You would like to use Azure Machine Learning to uncover data patterns and groupings. Which machine learning algorithm is the best choice? a) Clustering b) Classification c) Regression d) Reinforcement Learning
a) Clustering
. You are using Azure Machine Learning designer to create a training pipeline for a binary classification model. You have 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 was not used for training. Which additional kind of module should you add? a) Join Data b) Split Data c) Select Columns in Dataset
b) Split Data
Azure Speech Services can be used in a variety of applications. Which of the following correctly matches the use case with the appropriate speech service? (Choose 2 answers) a) Use case: Create closed captions for a recorded video Service: Speech-to-Text b) Use case: Read a text message aloud Service: Text-to-Speech c) Use case: Dictate a note or text message Service: Speech Translation d) Use case: Identify user sentiment in a recorded voice message Service: Speech-to-Text
a) Use case: Create closed captions for a recorded video Service: Speech-to-Text b) Use case: Read a text message aloud Service: Text-to-Speech
Which of the following features are supported by the Azure Text Analytics API? (Choose 2 answers) a) language detection b) named entity recognition c) text to speech services d) text identification in an image
a) language detection b) named entity recognition
Which of the following results does an object detection model typically return for an image? a) A class label and probability score for the image b) Bounding box coordinates that indicate the region of the image where all of the objects it contains are located c) A class label, probability, and bounding box for each object in the image
c) A class label, probability, and bounding box for each object in the image
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.
You are building an application that allows you to search the transcripts of recorded conversations from your customer support call center. Which Azure Cognitive Service would you use to convert audio from call center conversations into text? a) Speech-to-Text b) Text-to-Speech c) Language Understanding (LUIS) d) Text Analytics
a) Speech-to-Text
Which of the following are examples of data transformation modules available in Azure Machine Learning designer? (Choose 2 answers) a) Split Data b) Clean Missing Data c) Dataset d) Train Model
a) Split Data b) Clean Missing Data
You plan to use the Computer Vision service to read text in a large PDF document. Which API should you use? a) The Read API b) The OCR API c) The Recognize Text API
a) The Read API (it's better suited for larger images & runs asynchronously so it will not block your application while it is running. OCR isn't good for large files)
Which of the following application features uses Natural Language Processing (NLP)? (Choose 2 answers) a) Analyze written text and highlight key phrases. b) Translate text from one language to another. c) Translate a hand written note contained in an image into text. d) Locate text that is included in an image
a) Analyze written text and highlight key phrases. b) Translate text from one language to another.
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
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.
Which of the following is not a capability of the Azure Computer Vision service? (Choose 2 answers) a) Detect printed or handwritten text found in an image. b) Identify the type of image (clip art, line drawing, etc) c) Train a custom model to identify domain-specific entities in an image. d) Extract text and key/value pairs from documents.
c) Train a custom model to identify domain-specific entities in an image. d) Extract text and key/value pairs from documents.
You want to build a web-based application that uses conversational AI to answer a variety of user questions. Which Azure service is the best choice? a) Azure Bot Service b) Translator c) Text Analytics d) Speech Translation
a) Azure Bot Service
In Azure Cognitive Services, what is a QnA knowledge base? a) A data set that includes question and answer pairs. b) A data set that includes a list of utterances and intents. c) A data set that includes a set of industry-specific terms and the corresponding definition. d) A database that includes training data sets for a variety of conversational AI scenarios.
a) A data set that includes question and answer pairs.
You are using Azure's Computer Vision service to identify objects in an image. You are using the computer vision REST endpoint, and the JSON response includes one or more objects that have been identified. Along with each object's name, what other information is also included with each object in the JSON response? (Choose 2 answers) a) A bounding box (coordinates) that identifies the object's location in the image. b) A confidence score that indicates how likely an object identified correctly matches the content in the image. c) A count of how many objects of that type have been found. d) A URL to locate a full description of the object.
a) A bounding box (coordinates) that identifies the object's location in the image. b) A confidence score that indicates how likely an object identified correctly matches the content in the image.
You are using Azure's Computer Vision service to suggest tags that describe features identified in an image. You are using the computer vision REST endpoint, and the JSON response includes one or more tags that have been identified. What other information is also included with each tag in the JSON response? a) A confidence score that indicates how likely the tag correctly matches the content in the image. b) A set of coordinates given by a bounding box that identifies the tag's location in the image. c) A URL that provides a full description of the tag. d) A count indicating how many times the tag is found in the image.
a) A confidence score that indicates how likely the tag correctly matches the content in the image.
You have just trained and published an Azure Language Understanding (LUIS) model. You plan to use the REST endpoint in your application to respond to user questions and commands. When you send a user question or command to the REST endpoint for your LUIS model, what information is included in the response? (Choose 2 answers) a) A list of intents with a confidence score. b) A list of potential utterances with a confidence score. c) A list of entities extracted from the input question/command. d) The language of the input question/command.
a) A list of intents with a confidence score. c) A list of entities extracted from the input question/command.
When setting up an Azure AutoML experiment, which of the following configuration values are specified for the experiment? Select two answers. a) A primary metric used to compare the results of individual experimental runs. b) A list of blocked algorithms that should be excluded from the training runs. c) The hostname where the best model from the experimental runs should be deployed. d) The maximum time allowed to run all experimental runs.
a) A primary metric used to compare the results of individual experimental runs. b) A list of blocked algorithms that should be excluded from the training runs.
Calling the Detect API provided by the Azure Face service returns various information about the faces found in an image. Which of the following are examples of the information returned by this service? (Choose 2 answers) a) A set of face landmarks. b) A list of accessories (such as glasses) worn by the subject. c) The subject's eye color. d) A flag indicating whether the subject is a celebrity.
a) A set of face landmarks. b) A list of accessories (such as glasses) worn by the subject.
You are creating a bot using Azure Bot Service with QnA Maker as its knowledge base. Which of the statements regarding bot communication channels are correct? (Choose 2 answers) a) A web chat channel is automatically created for you when you create a bot. b) It is possible to send messages to and receive messages from a bot service using Microsoft Teams. c) Communicating with a bot service through an email channel is not supported. d) A bot service can be associated with only one communication channel.
a) A web chat channel is automatically created for you when you create a bot. b) It is possible to send messages to and receive messages from a bot service using Microsoft Teams.
You are using Azure Machine Learning to develop a model to predict whether a driver is a high or low risk driver for automobile insurance. Which of the following metrics can you use to compare the results of two or more models? a) AUC (Area under the Receiver Operating Characteristic Curve) b) r2_score c) root_mean_squared_error d) mean_absolute_error
a) AUC (Area under the Receiver Operating Characteristic Curve)
You are working on an application that supports an automation line in a factory. Several sensors provide data about equipment health, and you would like to use this data in real-time to identify potential line issues quickly. Which Azure cognitive service would be a good choice to help quickly identify issues based on your sensor data? a) Anomaly Detector b) Azure Monitor c) Form Recognizer d) Azure Auto Machine Learning
a) Anomaly Detector
Which statement about Azure Automated Machine Learning (AutoML) is true? (Choose 2 answers) a) AutoML is used to automatically select the best machine learning algorithm for your dataset. b) You can choose to use either the Python SDK or a no-code user interface to build an AutoML experiment. c) In order to use AutoML, developers must have a strong understanding of various machine learning algorithms. d) An AutoML will not perform a train-test split operation; you must provide both a train and test dataset for a an AutoML experiment.
a) AutoML is used to automatically select the best machine learning algorithm for your dataset. b) You can choose to use either the Python SDK or a no-code user interface to build an AutoML experiment.
You want to create a model to predict sales of ice cream based on historic data that includes daily ice cream sales totals and weather measurements. Which Azure service should you use? a) Azure Machine Learning b) QnA Maker c) Text Analytics
a) Azure Machine Learning
You work for an analytics company and are working on an application to detect credit card fraud. You want to create a model to predict whether or not a particular credit card transaction is fraudulent. You have historical transaction data to build your model. Which Azure Service should you use to build this model? a) Azure Machine Learning b) Anomaly Detection c) Text Analytics d) Form Recognizer
a) Azure Machine Learning
Which Azure Machine Learning feature offers the ability to build and deploy no-code predictive models using a drag-and-drop interface? a) Azure Machine Learning designer b) Azure Automated ML c) Text Analytics d) QnA Maker
a) Azure Machine Learning designer
Which of the following statements best describes the characteristics of a classification model in Azure Machine Learning? (Choose 2 answers) a) Classification algorithms use labeled training data to build a model and predict the category (class) of yet unseen data items. b) Classification algorithms are an example of unsupervised machine learning. c) Classification algorithms take unlabeled data and groups the data into two or more categories (classes). d) Classification algorithms can predict both binary and multi-class classification problems.
a) Classification algorithms use labeled training data to build a model and predict the category (class) of yet unseen data items. d) Classification algorithms can predict both binary and multi-class classification problems.
You plan to use a set of images to train an object detection model, and then publish the model as a predictive service. You want to use a single Azure resource with the same key and endpoint for training and prediction. What kind of Azure resource should you create? a) Cognitive Services b) Custom Vision c) Computer Vision
a) Cognitive Services
You are planning to use the Azure Face service to provide face recognition services for your organization. However, before you can use this feature, what steps do you first need to take? a) Create a PersonGroup and add images for each person in the organization to train the model. b) Create a new classification model using Azure Machine Learning, and train the model using labeled images of each person in the organization. c) Use Azure Custom Vision to train a model using labeled images of each person in the organization. d) Use the Computer Vision Face API to train the model from images of each person in the organization.
a) Create a PersonGroup and add images for each person in the organization to train the model.
You need to deliver a support bot for internal use in your organization. Some users want to be able to submit questions to the bot using Microsoft Teams, others want to use a web chat interface on an internal web site. What should you do? a) Create a knowledge base. Then create a bot for the knowledge base and connect the Web Chat and Microsoft Teams channels for your bot b) Create a knowledge base. Then create two bots that use the same knowledge base - one bot connected to the Microsoft Teams channel, and the other to the Web Chat channel. c) Create two knowledge bases with the same question and answer pairs. Then create a bot for each knowledge base; one connected to the Microsoft Teams channel, and the other to the Web Chat channel
a) Create a knowledge base. Then create a bot for the knowledge base and connect the Web Chat and Microsoft Teams channels for your bot
. 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
You are working on an application that uses computer vision to identify unwanted plant species growing alongside crops in farmer's fields. Which Azure Cognitive Service is the best choice to help you train your image classification model? a) Custom Vision b) Computer Vision c) Anomaly Detector d) Azure Machine Learning clustering analysis
a) Custom Vision
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
You are authoring a Language Understanding application to support an international clock. You want users to be able to ask for the current time in a specified city, for example "What is the time in London?". What should you do? a) Define a "city" entity and a "GetTime" intent with utterances that indicate the city intent. b) Create an intent for each city, each with an utterance that asks for the time in that city. c) Add the utterance "What time is it in city" to the "None" intent.
a) Define a "city" entity and a "GetTime" intent with utterances that indicate the city intent. (The intent encapsulates the task (getting the time) and the entity specifies the item to which the intent is applied (the city).)
You would like to have your web chatbot application support speech output. Which of the following channels would you need to configure for your bot service? a) Direct Line channel b) Custom channel c) Voice channel d) Speech channel
a) Direct Line channel
You are working on an AI system using Azure Cognitive Services Custom Speech to Text service. You want to ensure that your solution addresses the Inclusiveness responsible AI principle. Which step could you take to best enable your solution to empower and engage everyone? a) Enlist customers and early adopters to provide input to help train the model prior to general product availability b) Include a larger set of audio input files to train the model. c) Increase the threshold for the primary metric used to evaluate your model. d) Increase the number of audio files used in the test data set used to evaluate your model.
a) Enlist customers and early adopters to provide input to help train the model prior to general product availability
Which of the following Azure Cognitive Services can be integrated with Azure Bot Services as the engine that recognizes user intent to create an interactive chatbot application? a) Language Understanding (LUIS) b) Custom Vision c) Anomaly Detector d) Text Analytics
a) Language Understanding (LUIS)
You are using Azure Machine Learning to develop a machine learning model to predict fuel efficiency (miles/gallon) for automobiles manufactured between 2000 and 2010. The following information is provided for each automobile in the dataset: mpg (miles per gallon) number of cylinders horsepower weight model year manufacturer car name (model) Which of the following statements about the data set and machine learning model are correct? (Choose 2 answers) a) MPG (miles per gallon) is the label for this machine learning model. b) MPG (miles per gallon) is a feature for this machine learning model. c) The car name (model) is the label for this machine learning model. d) The manufacturer is an example of a potential feature for this machine learning model.
a) MPG (miles per gallon) is the label for this machine learning model. d) The manufacturer is an example of a potential feature for this machine learning model.
You need to use the Translator Text service to translate email messages from Spanish into both English and French. What is the most efficient way to accomplish this goal? a) Make a single call to the service; specifying a "from" language of "es", a "to" language of "en", and another "to" language of "fr". b) Make a single call to the service; specifying a "from" language of "es", and a "to" language of "en-fr". c) Make two calls to the service; one with a "from" language of "es" and a "to" language of "en", and another with a "from" language of "es" and a "to" language of "fr"
a) Make a single call to the service; specifying a "from" language of "es", a "to" language of "en", and another "to" language of "fr" (You can specify a single "from" language and multiple "to" languages.)
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
Which of the following statements about Azure Optical character recognition (OCR) is true? (Choose 2 answers) a) Optical character recognition (OCR) is part of the Azure Computer Vision API. b) Optical character recognition (OCR) locates and extracts text found in an image. c) Optical character recognition (OCR) cannot recognize handwritten text in an image. d) Optical character recognition (OCR) only supports print text written in English.
a) Optical character recognition (OCR) is part of the Azure Computer Vision API. b) Optical character recognition (OCR) locates and extracts text found in an image.
Which of the following Azure Cognitive Services would you choose to help build a conversational client application using artificial intelligence to answer customer questions? a) QnA Maker b) Text Analytics c) Form Recognizer d) Content Moderator
a) QnA Maker
A customer support team would like to implement an interactive chat window on their product website that uses artificial intelligence (AI) to answer customer questions. The team already has extensive frequently asked questions (FAQ) documentation available. Which Azure AI solutions should this team use to build a chat program from their existing FAQ documentation? a) QnA Maker + Azure Bot Service b) LUIS (Language Understanding) + Azure Functions c) Text Analytics + Azure Bot Service d) Form Recognizer + Azure Functions
a) QnA Maker + Azure Bot Service
You plan to integrate Azure QnA Maker with Azure Bot Services to build a conversational AI system to help answer user questions. What information do you need to configure a new Azure Bot to connect with your QnA knowledge base? (Choose 3 answers) a) QnA authorization key b) QnA endpoint hostname c) QnA knowledge base ID d) QnA app service name
a) QnA authorization key b) QnA endpoint hostname c) QnA knowledge base ID
You are using Azure Machine Learning to develop a machine learning model to predict fuel efficiency (miles/gallon) for automobiles manufactured between 2000 and 2010. Which machine learning algorithm would be the best choice for building this model? a) Regression b) Classification c) Clustering d) Reinforcement learning
a) Regression
Which of the following types of machine learning problems are supported with Azure Automated Machine Learning (AutoML)? (Choose 3 answers) a) Regression b) Classification c) Time-series forecasting d) Clustering
a) Regression b) Classification c) Time-series forecasting
You are working on an application that uses Azure Machine Learning to predict the correct medication and dosage for a patient based on their symptoms. The application must undergo rigorous testing and validation before product launch to ensure patients are given the proper medication. Which responsible AI practice is addressed with proper testing and validation? a) Reliability and safety b) Continuous improvement c) Accountability d) Inclusiveness
a) Reliability and safety
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
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
You are writing an application that analyzes customer product reviews and flags reviews that have a negative sentiment. Which Azure Cognitive Service would you use to provide sentiment analysis and mark text as positive, negative, or neutral? a) Text Analytics API b) Language Understanding (LUIS) c) Speech Translation d) Content Moderator
a) Text Analytics API
Using Azure Machine Learning designer, you have just developed and deployed a machine learning model to predict a used car's price, given key pieces of information about the car. You are now ready to call the deployed model for predictions from an application you are building. What information do you need to make a price prediction using the deployed model? (Choose 2 answers) a) The REST endpoint URL for the deployed model. b) Authentication key. c) Resource group ID d) Subscription ID
a) The REST endpoint URL for the deployed model. b) Authentication key.
What key piece of information do you need to call your QnA Maker service from a client application? a) The REST endpoint URL for your QnA Maker service b) The globally unique QnA Maker application name c) The hostname for the machine hosting your QnA Maker service d) The region where your QnA Maker service is deployed
a) The REST endpoint URL for your QnA Maker service
Which statements about Azure Speech Services capabilities are true? (Choose 2 answers) a) The Speech-to-Text API provides a batch transcript API that can be used to batch process larger audio files. b) When using the Text-to-Speech API, you can configure speech settings such as speed and volume. c) The Text-to-Speech and Speech-to-Text APIs support only the English language. d) Speech Translation is available through both the SDK and the REST API
a) The Speech-to-Text API provides a batch transcript API that can be used to batch process larger audio files. b) When using the Text-to-Speech API, you can configure speech settings such as speed and volume.
You use the Text Analytics 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.
You have published your Language Understanding application. What information does a client application developer need to get predictions from it? a) The endpoint and key for the application's prediction resource b) The endpoint and key for the application's authoring resource c) The Azure credentials of the user who published the Language Understanding application
a) The endpoint and key for the application's prediction resource
When using Azure Cognitive Services, which of the following is not a common computer vision task? a) Translate text found in an image from one language to another. b) Detect human faces within an image. c) Detect handwritten text within an image. d) Classify an image based on what the image contains.
a) Translate text found in an image from one language to another.
Azure Vision services can be used in a variety of applications. Which of the following correctly matches the use case with the appropriate Vision service? (Choose 2 answers) a) Use case: A social media application that automatically identifies and tags known friends in images. Service: Face service b) Use case: Extract information such as transaction time, merchant information, and totals from a receipt. Service: Form Recognizer c) Use case: Identify a celebrity in an image. Service: Face service d) Use case: Identify adult or racy content in an image. Service: Face service
a) Use case: A social media application that automatically identifies and tags known friends in images. Service: Face service b) Use case: Extract information such as transaction time, merchant information, and totals from a receipt. Service: Form Recognizer
You are using Azure Machine Learning designer to train and evaluate a machine learning model. You cannot find a built-in module to complete a data transformation step needed to complete your workflow. Which of the following options is the best choice for you to complete the required data transformation? a) Use the Execute Python Script module with custom Python code written to perform the data transformation. b) Use Azure AutoML instead of Azure Machine Learning designer. c) Cleanse and transform the training data before importing into Azure Machine Learning designer. d) Build your training model using the Azure Machine Learning APIs instead of Azure Machine Learning designer.
a) Use the Execute Python Script module with custom Python code written to perform the data transformation.
You are designing an AI application that uses computer vision to detect cracks in car windshields, and warns drivers when a windshield should be repaired or replaced. When tested in good lighting conditions, the application successfully detects 99% of dangerously damaged glass. Which of the following statements should you include in the application's user interface? a) When used in good lighting conditions, this application can be used to identify potentially dangerous cracks and defects in windshields. If you suspect your windshield is damaged, even if the application does not detect any defects, you should have it inspected by a professional. b) This application detects damage in your windshield. If the application detects a defect, have the windshield replaced or repaired. If no defect is detected, you're good to go! c) This application detects damage in any glass surface, but you must accept responsibility for using it only in appropriate lighting conditions.
a) When used in good lighting conditions, this application can be used to identify potentially dangerous cracks and defects in windshields. If you suspect your windshield is damaged, even if the application does not detect any defects, you should have it inspected by a professional.
Which of the following statements are true about the data used to train and evaluate a machine learning model? a) You should split the data set into two datasets; one dataset is used to train the model, and the other dataset to evaluate the model. b) You should always use the same data to evaluate the model that you used to train it. c) The only time you need to split a dataset into training and test sets is when using a regression algorithm. d) When splitting a dataset into training and test datasets, the data should remain in order with the first 70 - 80% of the data included in the training dataset, and the remaining rows in the test dataset.
a) You should split the data set into two datasets; one dataset is used to train the model, and the other dataset to evaluate the model.
You are using Azure Machine Learning to develop a machine learning model to predict fuel efficiency (miles/gallon) for automobiles manufactured between 2000 and 2010. The following information is provided for each automobile in the dataset: mpg (miles per gallon) | number of cylinders | horsepower | weight | model year | car name Currently, the car name includes both the manufacturer and the car model (ex. "honda civic"). You would like to break the car name into two separate pieces of data (columns): manufacturer and model. What is the term used to describe this type of data processing before training a model? a) feature engineering b) feature selection c) normalization d) data splitting
a) feature engineering
Which term completes the following definition of an Azure Machine Learning concept? A(n) ____________ is a workflow you build to manage the data and modules used to train and evaluate a machine learning model. a) pipeline b) experiment c) jupyter notebook d) workspace
a) pipeline
You are using Azure Machine Learning to develop a model to predict housing prices in the Boston area, given a large real estate dataset. Which of the following metrics can you use to compare the results of two or more models? (Choose 2 answers) a) r2_score b) normalized_root_mean_squared_error c) accuracy d) confusion matrix
a) r2_score b) normalized_root_mean_squared_error
Which of the following types of applications are a common consumer of Azure Cognitive Services' QnA Maker? (Choose 2 answers) a) social media applications b) chatbots c) language translation applications d) applications used to review and moderate content (text and audio)
a) social media applications b) chatbots
You are training an Azure Language Understanding (LUIS) model, and you plan to use with an interactive application that responds to user questions/commands. For example, a user may ask, "What is the temperature in Boston today?" What is the term used to describe what the user might say to the application, in this case asking about the temperature in Boston? a) utterance b) entity c) intent d) key phrase
a) utterance
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
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 (use the Assign Data to Clusters module to generate cluster predictions from a trained clustering model)
You want to extract text from images and then use the Text Analytics 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) Text Analytics
b) Cognitive Services
You want to use the Computer Vision service to analyze images. You also want to use the Text Analytics 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
You want to train a model that classifies images of dogs and cats based on a collection of your own digital photographs. Which Azure service should you use? a) Azure Bot Service b) Custom Vision c) Computer Vision
b) Custom Vision
What is one aspect that may impair facial detection? a) Smile expression b) Extreme angles c) Fast shutter speed
b) Extreme angles
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 (The Computer Vision resource type does not include the Form Recognizer service)
Your organization has an existing frequently asked questions (FAQ) document. You need to create a QnA Maker knowledge base that includes the questions and answers from the FAQ with the least possible effort. What should you do? a) Create an empty knowledge base, and then manually copy and paste the FAQ entries into it. b) Import the existing FAQ document into a new knowledge base. c) Import a pre-defined chit-chat data source.
b) Import the existing FAQ document into a new knowledge base.
You want to use the Text Analytics 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 (Key phrases can be used to identify the main talking points in a text document.)
You need to provision an Azure resource that will be used to author a new Language Understanding application. What kind of resource should you create? a) Text Analytics b) Language Understanding c) Cognitive Services
b) Language Understanding
You are creating a training pipeline for a regression model, using 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 based 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) Normalize Data c) Clean Missing Data
b) Normalize Data
_________ occurs when a model matches training data so closely that it doesn't generalize well to other data. a) Underfitting b) Overfitting c) Drift d) Root mean squared error
b) Overfitting
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) Time series forecasting
b) Regression
You are developing an application that must take English input from a microphone and generate a real-time text-based transcription in Hindi. Which service should you use? a) Translator Text b) Speech c) Text Analytics
b) Speech (The Speech service can translate from audio sources to text.)
Why do we split our data into training and validation sets? a) Data is split into two sets in order to create two models, one model using the training set and a different model using the validation set. b) Splitting data into two sets enables you to compare the labels that the model predicts with the actual known labels in the original dataset. c) We only need to split our data when we use the Azure Machine Learning Designer, not in other machine learning scenarios.
b) Splitting data into two sets enables you to compare the labels that the model predicts with the actual known labels in the original dataset.
.You want to use the Speech service to build an application that reads incoming email message subjects aloud. Which API should you use? a) Speech-to-Text b) Text-to-Speech c) Translate
b) Text-to-Speech
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 c) The project ID, iteration number, and the key and endpoint for the training resource.
b) The project ID, the model name, and the key and endpoint for the prediction resource
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
You plan to build an application that uses the Speech service to transcribe audio recordings of phone calls into text, and then submits the transcribed text to the Text Analytics service to extract key phrases. You want to manage access and billing for the application services in a single Azure resource. Which type of Azure resource should you create? a) Speech b) Text Analytics c) Cognitive Services
c) Cognitive Services
You want to use Face to identify named individuals. What must you do? a) Use the Computer Vision service - Face cannot perform facial recognition b) Use Face to retrieve age and emotional state for each person c) Use Face to create a group containing multiple images of each named individual, and train a model based on the group
c) Use Face to create a group containing multiple images of each named individual, and train a model based on the group (Creating a group that contains multiple images of named individuals enables you to train a facial recognition 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
