High quality 70-774 Exam Questions 2021

NEW QUESTION 1
You are building an Azure Machine Learning experiment.
You are preparing the output of a Boosted Decision Tree Regression module. You add a Normalize Data module to the experiment.
You need to ensure that the range of the transformation method produces an output on a scale of -1 to 1. Which transformation method should you use?

• A. MinMax
• B. TanH
• C. Logistic
• D. Zscore
• E. LogNormal

Answer: D

NEW QUESTION 2
You plan to use the Data Science Virtual Machine for development, but you are unfamiliar with R scripts. You need to generate R code for an experiment.
Which IDE should you use?

• A. XgBoost
• B. Rattle
• C. Vowpal Wabbit
• D. R Tools for Visual Studio

Answer: C

Explanation: References:
https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/provision-vm

NEW QUESTION 3
Note: This question is part of a series of questions that use the same or similar answer choices. An answer choice may be correct for more than one question in the series. Each question is independent of the other questions in this series. Information and details provided in a question apply only to that question.
You need to transform the columns in a dataset. The resulting data must be mean centered and have a variance of L The solution must use a native module.
Which module should you use?

• A. Execute Python Script
• B. Import Data
• C. Edit Metadata
• D. Select Columns in Dataset
• E. Clean Missing Data
• F. Tune Model Hyperparameters
• G. Clip Values
• H. Normalize Data

Answer: H

NEW QUESTION 4
Note: This question is part of a series of questions that use the same or similar answer choices. An answer choice may be correct for more than one question in the series. Each question is independent of the other questions in this series. Information and details provided in a question apply only to that question.
You need to use only one percent of an Apache Hive data table by conducting random sampling by groups. Which module should you use?

• A. Execute Python Script
• B. Tune Model Hyperparameters
• C. Normalize Data
• D. Select Columns in Dataset
• E. Import Data
• F. Edit Metadata
• G. Clip Values
• H. Clean Missing Data

Answer: A

Explanation: References:
https://docs.microsoft.com/en-us/azure/machine-learning/team-data-science-process/sample-data-hive

NEW QUESTION 5
You need to create a training set for use with a linear regression model, and then to test the training set.
How should you create the training set? To answer, drag the appropriate modules to the correct locations. Each module may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.

Answer:

Explanation: C:UserswkDesktopmudassarUntitled.jpg

NEW QUESTION 6
You have data about the following:
You need to predict whether a user will like a particular movie. Which Matchbox recommender should you use?

• A. Item Recommendation
• B. Related Items
• C. Rating Prediction
• D. Related Users

Answer: C

Explanation: References:
https://msdn.microsoft.com/en-us/library/azure/dn905970.aspx#RatingPredictionOptions

NEW QUESTION 7
You are building an Azure Machine Learning solution for an online retailer.
When a customer selects a product, you need to recommend products that the customer might like to purchase at the same time. The recommendation should be based on what other customers purchased when they purchased the same product.
Which model should you use?

• A. Collaborative filtering
• B. Boosted Decision Tree Regression model
• C. Two-Class boosted decision tree
• D. K-Means Clustering

Answer: A

NEW QUESTION 8
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
Start of repeated scenario
You plan to use Azure platform tools to detect and analyze food items in smart refrigerators. To provide families with an integrated experience for grocery shopping and cooking, the refrigerators will connect to other smart appliances, such as stoves and microwave ovens, on a LAN.
You plan to build an object recognition model by using the Microsoft Cognitive Toolkit. The object recognition model will receive input from the connected devices and send results to applications.
The training data will be derived from more than 10 TB of images. You will convert the raw images to the sparse format.
End of repeated scenario.
You need to ensure that a web service endpoint can receive image data and use an object recognition model to return the expected object and the confidence level of the model. The solution must minimize the effort required to generate the client code to access the web service.
Which resource should you use?

• A. the edX Data Science Learning Dashboard
• B. Azure Machine Learning Studio
• C. Cortana Intelligence Gallery
• D. the Data Science Virtual Machine

Answer: B

NEW QUESTION 9
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
Start of repeated scenario
You plan to use Azure platform tools to detect and analyze food items in smart refrigerators. To provide families with an integrated experience for grocery shopping and cooking, the refrigerators will connect to other smart appliances, such as stoves and microwave ovens, on a LAN.
You plan to build an object recognition model by using the Microsoft Cognitive Toolkit. The object recognition model will receive input from the connected devices and send results to applications.
The training data will be derived from more than 10 TB of images. You will convert the raw images to the sparse format.
End of repeated scenario.
You need to preprocess the training data by using a Principal Component Analysis (PCA) algorithm in the least amount of time possible. Which implementation method should you use?

• A. Azure HDInsight using HiveML
• B. Azure Machine Learning Studio and a custom Execute Python Script module
• C. Azure HDInsight using Microsoft R Server
• D. Azure Machine Learning Studio with a custom Execute R Script module

Answer: C

NEW QUESTION 10
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
A travel agency named Margie’s Travel sells airline tickets to customers in the United States.
Margie’s Travel wants you to provide insights and predictions on flight delays. The agency is considering implementing a system that will communicate to its customers as the flight departure nears about possible delays due to weather conditions. The flight data contains the following attributes:
The weather data contains the following attributes: AirportID, ReadingDate (YYYY/MM/DD HH), SkyConditionVisibility, WeatherType, WindSpeed, StationPressure, PressureChange, and HourlyPrecip.
You plan to predict flight delays that are 30 minutes or more.
You need to build a training model that accurately fits the data. The solution must minimize over fitting and minimize data leakage.
Which attribute should you remove?

• A. OriginAirportID
• B. DepDel
• C. DepDel30
• D. Carrier
• E. DestAirportID

Answer: C

NEW QUESTION 11
You have the following three training datasets for a restaurant:
You must recommend restaurant to a particular user based only on the users features. You need to use a Matchbox Recommender to make recommendations.
How many input parameters should you specify?

• A. 1
• B. 2
• C. 3
• D. 4

Answer: B

Explanation: References:
https://msdn.microsoft.com/en-us/library/azure/dn905987.aspx

NEW QUESTION 12
Note: This question is part of a series of questions that use the same scenario. For your convenience, the scenario is repeated in each question. Each question presents a different goal and answer choices, but the text of the scenario is exactly the same in each question in this series.
A travel agency named Margie’s Travel sells airline tickets to customers in the United States.
Margie’s Travel wants you to provide insights and predictions on flight delays. The agency is considering implementing a system that will communicate to its customers as the flight departure nears about possible delays due to weather conditions. The flight data contains the following attributes:
The weather data contains the following attributes: AirportID, ReadingDate (YYYY/MM/DD HH), SkyConditionVisibility, WeatherType, WindSpeed, StationPressure, PressureChange, and HourlyPrecip.
You have an untrained Azure Machine Learning model that you plan to train to predict flight delays.
You need to assess the variability of the dataset and the reliability of the predictions from the model. Which module should you use?

• A. Cross-Validate Model
• B. Evaluate Model
• C. Tune Model Hyperparameters
• D. Train Model
• E. Score Model

Answer: A

Explanation: References:
https://msdn.microsoft.com/en-us/library/azure/dn905852.aspx

NEW QUESTION 13
You are building an Azure Machine Learning workflow by using Azure Machine Learning Studio. You create an Azure notebook that supports the Microsoft Cognitive Toolkit.
You need to ensure that the stochastic gradient descent (SGD) configuration maximizes the samples per second and supports parallel modeling that is managed by a parameter server.
Which SGD algorithm should you use?

• A. DataParallelASGD
• B. DataParallelSGD
• C. ModelAveragingSGD
• D. BlockMomentumSGD

Answer: C

NEW QUESTION 14
You have data about the following:
• Users
• Movies
• User ratings of the movies
You need to predict whether a user will like a particular movie. Which Matchbox recommender should you use?

• A. Rating Prediction
• B. Related Users
• C. Item Recommendation
• D. Related Items

Answer: A

NEW QUESTION 15
Note: This question is part of a series of questions that use the same or similar answer choices. An answer choice may be correct for more than one question in the series. Each question is independent of the other questions in this series. Information and details provided in a question apply only to that question.
You have a dataset that contains a column named Column1. Some of the values in Column1 are empty. You need to replace the empty values by using probabilistic Principal Component Analysis (PCA). The
solution must use a native module.
Which module should you use?

• A. Execute Python Script
• B. Clean Missing Data
• C. Select Columns in Dataset
• D. Import Data
• E. Normalize Data
• F. Edit Metadata
• G. Tune Model Hyperparameters

Answer: B

NEW QUESTION 16
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this sections, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You are designing an Azure Machine Learning workflow.
You have a dataset that contains two million large digital photographs. You plan to detect the presence of trees in the photographs.
You need to ensure that your model supports the following:
Solution: You create a Machine Learning experiment that implements the Multiclass Decision Jungle module. Does this meet the goal?

• A. Yes
• B. No

Answer: B

NEW QUESTION 17
You plan to use the Import Data module to import data from a web URL by using HTTP. Which file format can you use as the source of the import operation?

• A. Optimized Row Columnar (ORQ
• B. Extensible Markup Language (XML)
• C. comma-separated value (CSV)
• D. JavaScript Object Notation (JSON)

Answer: D