Which of the following are NLP services in Microsoft Azure?

Translator Text, Language Understanding Intelligent Service (LUIS), Text Analytics

Natural language processing can be used to

Classify email messages as work-related or personal

Why do we split our data into training and validation sets?

To compare labels the model predicts with known labels in the dataset

Which type of computer vision is used in a mobile app for employees to scan and store their expenses while travelling?

Optical character recognition (OCR)

When using Face to detect human faces, how does the service indicate the location of the faces it detects?

A set of coordinates that define a bounding box around each face

You create a training pipeline in Azure ML designer for a classification model. What must be done before deploying it?

Create an inference pipeline from the training pipeline

What are two tasks that can be performed by using computer vision?

Detect brands in an image, Detect the color scheme in an image

You plan to use the Form Recognizer pre-built receipt model. Which kind of Azure resource should you create?

Form Recognizer or Cognitive Services resource

What are two tasks that can be performed by using the Computer Vision service?

Detect faces in an image, Recognize handwritten text

In which two scenarios can you use speech recognition?

Creating a transcript of a telephone call or meeting, Providing closed captions for recorded or live videos

Which of the following results does an object detection model typically return for an image?

A class label, probability, and bounding box for each object in the image

What should you use as a feature to train a model to predict the fare of a taxi journey?

Trip distance of individual taxi journeys

What helps us analyze images to find ones including one or more faces & at least one person wearing sunglasses?

the Detect operation in the Face service

What information do client application developers need to get predictions from your Language Understanding application?

Endpoint and key for the application's prediction resource

Using an existing FAQs, how can one create a QnA Maker knowledge with the least possible effort?

Import the existing FAQ document into a new knowledge base

Which two scenarios are examples of a conversational AI workload?

A chatbot that helps users find answers on a website themselves, Telephone voice menus to reduce the load on human resources

Which two scenarios are examples of a conversational AI workload?

A website that interactively responds to users questions, A smart device in the home that responds to questions

For a machine learning progress, how should you split data for training and evaluation

Randomly split the data into rows.

You want to use automated ML to train a regression model with the best possible R2 score. How should you configure this?

Set the Primary metric to R2 score

Which tasks require an enterprise workspace in Azure Machine Learning?

Using a GUI to define & run ML experiments from Azure ML designer., Using a graphical user interface (GUI) to run automated ML experiments.

studbud

AI900 - Practice Exam

97 termsStudBud Administration123 plays

Imported from external platform

Flashcards97 cardsFPractice quizPHost liveL

Questions 97

Answers

1
Which two AI services reduce the load on telephone operators with a chatbot to answer questions with predefined answers?
Translator Text
QnA Maker
Azure Bot Service
Text Analytics
2
Which of the following are NLP services in Microsoft Azure?
Translator Text
Language Understanding Intelligent Service (LUIS)
Text Analytics
Read & OCR
3
Which Azure service helps train a model that classifies images of dogs & cats based on a collection of your own photos?
All of the above
Azure Bot Service
Computer Vision
Custom Vision
4
For AI systems for self-driving cars to operate consistently during unexpected circumstances, which principle is applied
Reliability and safety
Inclusiveness
Fairness
Accountability
5
Natural language processing can be used to
Stop a process in a factory when extremely high temperatures are registered
Predict the number of future car rentals
Classify email messages as work-related or personal
Predict which website visitors will make a transaction
6
Why do we split our data into training and validation sets?
Only need to split data because we are using Azure ML Designer
The initial dataset is too large and will take time to train the model
To create 2 models, 1 uses the training set & the other, the validation set
To compare labels the model predicts with known labels in the dataset
7
Which single resource allows us to publish an object detection model with one key & endpoint for training & prediction?
Computer Vision
Cognitive Services
Custom Vision
Azure Vision Services
8
Which type of ML supports early detection of the different brain haemorrhage types in images?
Regression
Classification
Clustering
None of the above
9
Which type of computer vision is used in a mobile app for employees to scan and store their expenses while travelling?
Image classification
Optical character recognition (OCR)
Semantic segmentation
Object detection
10
Which metric can you use to evaluate a classification model?
Mean absolute error (MAE)
Root mean squared error (RMSE)
True positive rate
Coefficient of determination (R2)
11
You plan to use the Computer Vision service to read text in a large PDF document. Which API should you use?
The Recognize Text API
The OCR API
The Read API
The Text Analytics API
12
To transform numeric columns so that the values are on similar scales, which module should you add to the pipeline?
Scale Numeric Data
Clean Missing Data
Normalize Data
Select Columns in a Dataset
13
After building a ML model, what should you do to ensure that the model meets the Microsoft transparency principle?
Set Validation type to Auto.
Enable Explain best model.
Set Max concurrent iterations to 0.
Set Primary metric to accuracy.
14
When using Face to detect human faces, how does the service indicate the location of the faces it detects?
A set of coordinates that define a bounding box around each face
Two pairs of coordinates for each face, indicating the location of the eyes
Outline of each face it detects
A pair of coordinates for each face, indicating the center of the face
15
You create a training pipeline in Azure ML designer for a classification model. What must be done before deploying it?
Create an inference pipeline from the training pipeline
Clone the training pipeline with a different name
Add an Evaluate Model module to the training pipeline
Create a key and an endpoint
16
Which type of AI is used in a recycling machine that automatically identify bottles & rejects other items?
Natural language processing
Conversational AI
Computer vision
Anomaly detection
17
What is one aspect that may impair facial detection?
Extreme angles
Smile expression
Portrait orientation of images
Fast shutter speed
18
What are two tasks that can be performed by using computer vision?
Predict stock prices
Detect brands in an image
Translate text between languages
Detect the color scheme in an image
19
What are the Conversational AI services in Microsoft Azure?
QnA Maker
Custom Vision
Azure Bot Service
Text Analytics
20
Which type of computer vision is used to determine the location of cars in images for estimating distances between cars?
Object detection
Image classification
Optical character recogniser (OCR)
Face detection
21
Which type of AI workload can detect when a customer is upset based on what the customer types in the chatbot?
Regression
Semantic Segmentation
Anomaly detection
Natural Language Processing
22
From Azure ML designer, to deploy a real-time inference pipeline for others to consume, you must deploy the model to
Azure Container Instances
A local web service
Azure Kubernetes Service (AKS)
Azure Machine Learning compute
23
You plan to use the Form Recognizer pre-built receipt model. Which kind of Azure resource should you create?
Form Recognizer or Cognitive Services resource
Only Form Recognizer resource
Both resources must be used together
Computer Vision resource
24
What resource can be used to author a new Language Understanding application?
Cognitive Services
Language Understanding
Translate
Text Analytics
25
What are two tasks that can be performed by using the Computer Vision service?
Translate the text in an image between languages
Detect faces in an image
Recognize handwritten text
Train a custom image classification model
26
In which two scenarios can you use speech recognition?
An in-car system that reads text messages aloud
Creating a transcript of a telephone call or meeting
Providing closed captions for recorded or live videos
Creating an automated public address system for a train station
27
Which of the following results does an object detection model typically return for an image?
Bounding box coordinates that indicate where all of the objects are located
A class label, probability, a bounding box and the focus on the object
A class label, probability, and bounding box for each object in the image
A class label and probability score for the image
28
What should you use as a feature to train a model to predict the fare of a taxi journey?
Fare of individual taxi journeys
Trip ID of individual taxi journeys
Trip distance of individual taxi journeys
Number of taxi journeys in the dataset
29
What helps us analyze images to find ones including one or more faces & at least one person wearing sunglasses?
the Describe Image operation in the Computer Vision service
the Detect operation in the Face service
the Verify operation in the Face service
the Analyze Image operation in the Computer Vision service
30
A model predicts the price of an old car based on its make, model, engine size & mileage. What kind of ML model is used?
Regression
Clustering
Time series forecasting
Classification
31
What information do client application developers need to get predictions from your Language Understanding application?
Endpoint and key for the application's authoring resource
All of the above
Endpoint and key for the application's prediction resource
Azure credentials of the user publishing the Language Understanding app
32
Which two services should you use to develop a bot that will enable users to query a knowledge base by using NLP?
Form Recognizer
Azure Bot Service
Anomaly Detector
QnA Maker
33
You need to create a conversational support system based on the existing FAQs. Which service should you use?
Language Understanding (LUIS)
Computer vision
Text Analytics
QnA Maker
34
Using an existing FAQs, how can one create a QnA Maker knowledge with the least possible effort?
Import a pre-defined chit-chat data source
Import the existing FAQ document into a new knowledge base
Create an empty knowledge base & manually copy & paste FAQ entries into it
Import the FAQ answers to the knowledge base
35
When using Speech & Text Analytics to extract key phrases from transcribed calls, which single resource can be used?
Speech-to-Text
Cognitive Services
Speech
Text Analytics
36
Which two scenarios are examples of a conversational AI workload?
A telephone answering service that has a pre-recorder message
A chatbot that helps users find answers on a website themselves
A service that creates FAQ documents by crawling public websites
Telephone voice menus to reduce the load on human resources
37
When using Text Analytics to determine the key talking points in a text document, which feature should you use?
Entity detection
Key phrase extraction
Language detection
Sentiment analysis
38
When the sentiment analysis score of a document is 0.99, what can be inferred about the document sentiment?
The document is neutral.
The document is ambiguous.
The document is positive.
The document is negative.
39
Besides Score Model & Evaluate Model, which module is involved in testing a model with a validation data set?
Select Columns in Dataset
Subset Data
Split Data
Join Data
40
Which service should you use to extract text, key/value pairs, and table data automatically from scanned documents?
Form Recognizer
Text Analytics
Custom Vision
Ink Recognizer
41
Data values that influence the prediction of a model are called
Identifiers
Dependent variables
Features
Labels
42
With Text Analytics, which type of NLP should you use to identify the main talking points in a collection of documents?
Key Phrase Extraction
Entity Recognition
Language Detection
Sentiment Analysis
43
Which two scenarios are examples of a conversational AI workload?
A website that interactively responds to users questions
A smart device in the home that responds to questions
Assembly line machinery that autonomously inserts headlamps into cars
Monitoring the temperature to turn on fans when the temperature is too high
44
The ability to extract subtotals and totals from a receipt is a capability of which service?
Form Recognizer
Custom Vision
Text Analytics
Ink Recognizer
45
What is used to generate additional features?
Feature engineering
Model evaluation
Feature selection
Model training
46
For a machine learning progress, how should you split data for training and evaluation
Use labels for training and features for evaluation.
Randomly split the data into columns.
Use features for training and labels for evaluation.
Randomly split the data into rows.
47
You want to use automated ML to train a regression model with the best possible R2 score. How should you configure this?
Enable featurization
Set the Primary metric to R2 score
Set the Secondary metric to R2 score
Block all algorithms other than GradientBoosting
48
When using the pre-built receipt model in Form Recognizer, what is the maximum file size of JPG file you can submit?
2 MB
20 MB
5 MB
50 MB
49
While presenting at a conference, your session is transcribed into subtitles for the audience. This is an example of:
Sentiment Analysis
Speech Recognition
Speech Synthesis
Translation
50
Which two fields should you use as features to predict the income range of a given customer?
Education Level
Income Range
Age
Last Name
51
Which tasks require an enterprise workspace in Azure Machine Learning?
Create a compute instance to use as a workstation.
Using a GUI to define & run ML experiments from Azure ML designer.
Create a dataset from a comma-separated value (CSV) file
Using a graphical user interface (GUI) to run automated ML experiments.
52
Which module in Azure ML designer should be used to create a training and validation dataset from an existing dataset?
Split Data
Add Rows
Join Data
Select Columns in Dataset
53
While exploring voice recognition, identifying barriers that might leave out specific user groups is an example of ____
Privacy and security
Inclusiveness
Accountability
Fairness
54
When might you see NaN returned for a score in Language Detection?
When the score calculated by the service is outside the range of 0 to 1
When the language is not supported by Azure
When the language is ambiguous
When the predominant language in the text is mixed with other languages
55
Which AI service can you use to interpret the meaning of a user input such as 'Call me back later?'
Text Analytics
Speech
Language Understanding (LUIS)
Translator Text
56
When a binary classification model is evaluated and has an AUC score of 0.3, what can be concluded about the model?
It performs better than random guessing.
It performs worse than random guessing.
It can explain 30% of the variance between true and predicted labels.
It predicts accurately for 70% of test cases.
57
A banking system that predicts whether a loan will be repaid is an example of which machine learning?
None of the above
Clustering
Regression
Classification
58
When training a model, why should you randomly split the rows into separate subsets?
To train the model twice to attain better accuracy
To train multiple models simultaneously to attain better performance
To test the model by using data that was not used to train the model
All of the above
59
How do you use Computer Vision service to analyze images of locations and identify well-known buildings?
Retrieve the objects in the image.
Retrieve the categories for the image, specifying the celebrities domain
Retrieve the categories for the image, specifying the landmarks domain
Retrieve the tags in the image.
60
How do we deliver a bot such that users can submit questions via Microsoft Teams or a web chat interface?
Create two identical knowledge bases to make separate bots for each channel
Connect the Web Chat & Microsoft Teams channels to each other
Connect one bot to Microsoft Teams & the other bot to the Web Chat
Connect a single bot to the Web Chat & Microsoft Teams channels
61
Which AI service should you use to create a bot from a frequently asked questions (FAQ) document?
Text Analytics
QnA Maker
Speech
Language Understanding (LUIS)
62
A NLP solution analyzes customer reviews & determines how positive or negative they are. Which type of NLP workload?
Sentiment Analysis
Key Phrase Extraction
Language Detection
Entity Recognition
63
Which service will allow users to interact with a web app that will guide them to the best resource or answer?
Custom Vision
Face
Translator Text
QnA Maker
64
Which API should you use when using Speech for an application that reads incoming email message subjects aloud?
Speech
Text-to-Speech
Speech-to-Text
Translate
65
Which module should you use to infer cluster predictions from a clustering model?
Train Clustering Model
Infer Clusters
Assign Data to Clusters
Score Model
66
When building AI systems, what should be done to ensure that the service meets the transparency principle?
All visuals have an associated text that can be read by a screen reader.
Provide documentation to help developers debug code
Ensure that a training dataset is representative of the population
Enable autoscaling to ensure that a service scales based on demand
67
Which version service is used to build an app that reads instructions aloud to support users who have reduced vision?
Speech
Translator Text
Text Analytics
Language Understanding (LUIS)
68
What ML model is used to categorize loans as low/high risk based on the amount, the borrower's income & the loan period?
Clustering
Regression
Classification
Time series forecasting
69
Which configuration property of the K-Means Clustering module ensures a model assigns items to one of three clusters?
Set Iterations to 3
Set Number of Centroids to 3
Set Number of Clusters to 3
Set Random number seed to 3
70
Which type of machine learning should you use to predict the number of gift cards that will be sold next month?
None of the above
Classification
Regression
Clustering
71
What resource allows us to use Computer Vision & Text Analytics to analyze images & text but needs one key & endpoint?
Azure Bot Service
Custom Vision
Cognitive Services
Computer Vision
72
For a Language Understanding application of an international clock so users can ask for times in specified cities:
Create intents for each city with an utterance asking for time in each city
Define city entity & GetTime intent with utterances indicating the intent
None of the above
Add the utterance 'What time is it in city' to the None intent
73
The interactive answering of questions entered by a user as part of an application is an example of:
Anomaly detection
Forecasting
Computer vision
Conversational AI
74
Which two parameters should you use to consume an inference pipeline?
Training endpoint
REST endpoint
Model name
Authentication key
75
You want to use Face to identify named individuals. What must you do?
Use the Computer Vision service - Face cannot perform facial recognition
Use Face to retrieve age and emotional state for each person
Use Face to train a model based on multiple images of each individual
Use the Custom Vision service - For uploading your own images
76
You train an image classification model that achieves unsatisfactory evaluation metrics. How might you improve it?
Reduce the size of the images used to train the model.
Add a new label for "unknown" classes.
Add more specific labels.
Add more images to the training set.
77
Which service is used to develop conversational AI solutions that will communicate with users through multiple channels?
Translator Text
Text Analytics
Form Recognizer
Azure Bot Service
78
For a custom model to process product images & identify the products of competitors, which Azure service should you use?
Form Recognizer
Computer Vision
Face
Custom Vision
79
What should you use so that a bot uses user feedback to improve the relevance of the responses over time?
Active Learning
Key Phrase Extraction
Business Logic
Sentiment Analysis
80
You need to make the press releases of your company available in a range of languages. Which service should you use?
Speech
Language Understanding (LUIS)
Text Analytics
Translator Text
81
You have published an image classification model. What information must you provide to developers who want to use it?
The project ID, model name & key & endpoint for the training resource.
Only the project ID.
The project ID, model name & key & endpoint for both resources
The project ID, model name & key & endpoint for the prediction resource.
82
Which Azure service should you use to create a model to predict sales of ice cream based on historic data?
QnA Maker
Azure Machine Learning
None of the above
Text Analytics
83
AI systems empowering all, including those with hearing, visual & other impairments exhibits which Microsoft principle?
Accountability
Reliability and safety
Inclusiveness
Fairness
84
Using Custom Vision for image classification, which resource can only be used for model training & not prediction?
Computer Vision
Azure Machine Learning
Custom Vision
Cognitive Services
85
Which service allows us to take English input from a microphone & generate real-time text-based transcriptions in Hindi?
Speech
Speech Analytics
Translator Text
Text Analytics
86
In which two scenarios can you use the Form Recognizer service?
Extract the invoice number from an invoice
Identify the retailer from a receipt
Translate a form from French to English
Find image of product in a catalog
87
Which type of machine learning should be used to predict the sea level in meters for the next 10 years?
Classification
None of the above
Regression
Clustering
88
To extract text from images & analyse it with Text Analytics, which resource will allow us to have one key & endpoint?
Cognitive Services
Custom Vision
Text Analytics
Computer Vision
89
Which service should you use to determine a user's intent for a chatbot solution?
Language Understanding (LUIS)
QnA Maker
Speech
Translator Text
90
Which two components can you drag onto a canvas in Azure Machine Learning designer?
Pipeline
Module
Compute
Dataset
91
What are three ways to create question and answer text by using QnA Maker?
Generate the questions and answers from an existing webpage.
Train a ML model based on a file that contains the questions.
Import chit-chat content from a predefined data source.
Manually enter the questions and answers.
92
Which service can be used to train an object detection model by using your own images?
Form Recognizer
Computer Vision
Video Indexer
Custom Vision
93
Select the Microsoft guiding principles for responsible AI (may be more than one answer)
Decisiveness
Inclusiveness
Fairness
Knowledgeability
94
Predicting the hours of overtime a delivery person will work based on the number of orders received is an example of
Regression
None of the above
Clustering
Classification
95
What are the Computer Vision services in Microsoft Azure?
Custom Vision
Computer Vision
Cognitive Services
Text Analytics
96
Employees usually provide support to customers. What are the benefits of a bot that provides automated answers instead?
Reduced workload for the customer service agents
Increased sales
Improved product reliability
None of the above
97
Returning a bounding box that indicates the location of a vehicle in an image is an example of:
Image classification
Semantic segmentation
Object detection
Optical character recogniser (OCR)

AI900 - Practice Exam Flashcards | StudBud