AI-900 Flashcards
1
Q
You build a machine learning model by using the automated machine learning user interface (UI). You need to ensure that the model meets the Microsoft transparency principle for responsible AI. What should you do?
A
Enable Explain best model.
2
Q
Forecasting housing prices based on historical data is an example of anomaly detection?
A
False
3
Q
Identifying suspicious sign-ins by looking for deviations from usual patterns is an example of anomaly detection?
A
True
4
Q
Predicting whether a patient will develop diabetes based on the patients medical history is an example of anomaly detection?
A
False
5
Q
What is used to extract dates, quantities and locations from text?
A
Named Entity Recognition (NER)
6
Q
What is used to generate additional features?
A
Feature engineering
7
Q
You run a charity event that involves posting photos of people wearing sunglasses on Twitter. You need to ensure that you only retweet photos that meet the following requirements:
✑ Include one or more faces.
✑ Contain at least one person wearing sunglasses.
What should you use to analyze the images?
A
The detect operation in the Face service
8
Q
A triage bot that prioritises insurance claims based on injuries is an example of the Microsoft reliability and safety principle for responsible AI?
A
False
9
Q
You plan to deploy an Azure Machine Learning model as a service that will be used by client applications. Which three processes should you perform in sequence before you deploy the model? To answer, move the appropriate processes from the list of processes to the answer area and arrange them in the correct order.
A
Data preparation
Model training
Model evaluation
10
Q
According to Microsoft’s _______ principle of responsible AI, AI systems should NOT reflect biases from the data sets that are used to train the systems
A
fairness
11
Q
Data values that influence the prediction of a model are called ______.
A
Features
12
Q
You have a dataset that contains information about taxi journeys that occurred during a given period. You need to train a model to predict the fare of a taxi journey. What should you use as a feature?
A
The trip distance of individual taxi journeys
13
Q
Automated machine learning can automatically infer the training data from the use case provided.
A
False
14
Q
Automated machines learning works by running multiple training iterations that are scored and ranked by the metrics you specify?
A
True
15
Q
Automated machine learning enables you to specify a dataset and will automatically understand which label to predict?
A
False
16
Q
A banking system that predicts whether a loan will be repaid is an example of the __________ type of machine learning.
A
Classification
17
Q
Labelling is the process of tagging training data with known values.
A
True
18
Q
Accuracy is always the primary metric used to measure a model’s performance.
A
False
19
Q
Which service should you use to extract text, key/value pairs, and table data automatically from scanned documents?
A
Form recogniser
20
Q
From Azure Machine Learning designer, to deploy a real-time inference as a service for others to consumer, you must deploy the model to _________.
A
Azure Kubernetes Service (AKS)
21
Q
Azure Machine Learning designer provides a drag and drop virtual canvas to build, test and deploy machine learning models.
A
True
22
Q
Azure Machine Learning designer enables you to save your progress as a pipeline draft.
A
True
23
Q
Azure Machine Learning designer enable you to include customer JavaScript functions.
A
False
24
Q
Azure Machine Learning designer lets you create machine learning models by ________.
A
Adding and connecting modules on a visual canvas
25
Automated machine learning provides you with the ability to include custom Python scripts in a training profile.
True
26
A medical research project uses a large anonymized dataset of brain scan images that are categorized into predefined brain haemorrhage types. You need to use machine learning to support early detection of the different brain haemorrhage types in the images before the images are reviewed by a person. This is an example of which type of machine learning?
Classification
27
You are building a tool that will process images from retail stores and identify the products of competitors. The solution will use a custom model. Which Azure Cognitive Services service should you use?
Custom vision
28
What are two metrics that you can use to evaluate a regression model? Each correct answer presents a complete solution.
Coefficient of determination
Root mean squared error
29
Which metric can you use to evaluate a classification model?
True positive rate
30
The handling of unusual or missing values provided to an AI system is a consideration for the Microsoft _____ principle for responsible AI.
Reliability and safety
31
You are creating a company expense claim application. you wish to train a machine learning model using your own expense claim forms and labeled data. This is an example of ___________.
Supervised learning
32
The OCR API in Azure Computer Vision service is used to scan newspapers and magazines
False
33
You want to use some of your data for training a model and the remaining data for evaluation of the model. Which data transformation module do you have to add to your pipeline?
Split data
34
What is the maximum file size for the READ API
50MB
35
For a binary classification model, what does an AUC of 0.5 mean?
Your models performance is the same as random guessing of classes
36
Which service is used to suggest class and bounding boxes you add to training set after an initial dataset?
Tag smart
37
You are authoring a Language Understanding (LUIS) application to support a music festival. You want users to be able to ask questions about scheduled shows, such as: “Which act is playing on the main stage?”. The question “Which act is playing on the main stage?” is an example of which type of element?
An utterance
38
You build a QnA Maker bot by using a frequently asked questions (FAQ) page. You need to add professional greetings and other responses to make the bot more user friendly. What should you do
Add chit chat
39
What are the four types of Compute resources you can use in Azure Machine Learning Studio?
Attached compute
Compute instance
Compute clusters
Inference Clusters
40
You need to train and test your ML model. You prepare data for model training. Several of your numeric features have different scales. The first feature has a minimum value of 0.253 and a max of 0.987, the second one – from 12 to 124, and the last one – from 13545 to 56798. You need to bring them to a common scale. You decide to use feature engineering to address this problem. Does this decision help you to achieve your goal?
No, you need to normalise the numbers to bring them to a common scale
Feature engineering is a method of creating new features based on exisitng ones
41
You implement an aerial image processing application to identify the flooded areas. What common Computer Vision task is this application using?
Semantic segmentation (classifying pixels that belong to a particular object)
42
The customer service of your company spends a lot of time answering the same questions. They asked you to help them to automate this process. They provided you with a Microsoft Excel (*.xlsx) document with frequently asked questions and typical answers. What service will you use to create a knowledge base from this document?
QnA Maker
43
You are working for a car dealership. Your boss asks you to provide him forecast information: will the new car model be successful or not. The new model has a variety of engine improvements, more comfortable seats, and a sunroof. You compiled the list of data about previous successful models with their characteristics and sales numbers. What should you do in the pre-processing data stage that would help you to predict the success of the new model?
Feature selection - narrow down the feature which are important for label prediction and discard all features that don't play or play a minimal role in label prediction
44
The Text Analytics service can detect handwritten signatures in a document. True or False?
False
45
You are creating a solution that needs to identify if celebrities are present in images and also to determine their age. What capabilities should you take into account?
Detect faces
Detect domain-specific content
46
Suppose you’re creating a software system that tracks activity in an automated production line and you want it to be able to identify failures. What Al cognitive service should you implement in the development of the system?
Anomaly detector
47
Al should bring benefits to some part of society or some specific groups of people. True or False?
False
48
Detecting image color schemes is a capability of Computer vision service. True or False?
True
49
You work for a social media company and you need to implement an Al solution that can detect images that contain adult content or depict gory, violent scenes before they are posted and shared. Which Al workload should you use?
Content moderator
50
When working in Azure Machine Learning designer, it is possible to save your progress as a pipeline draft. True or False?
True
51
A company wants to build a recycling machine for plastic bottles. The recycling machine must automatically identify bottles of the correct shape and reject all other items. Which type of Al workload should the company use?
Computer vision
52
You’re creating a solution that counts the number of people present in an image. Which Computer Vision model can help you achieve the task?
Face detection
53
What is the first step in the statistical analysis of terms in a text in the context of natural language processing (NLP)?
Removing stop words
54
Which two Azure AI Services features can be used to enable both text-to-text and speech-to-text between multiple languages? Each correct answer presents part of the solution.
The speech service
the translator service
55
Which artificial intelligence (AI) technique serves as the foundation for modern image classification solutions?
Deep learning
56
Which computer vision solution provides the ability to identify a person's age based on a photograph?
Facial detection
57
Which two specialized domain models are supported by Azure AI Vision when categorizing an image? Each correct answer presents a complete solution
Celebrities and landmarks
58
Which computer vision service provides bounding coordinates as part of its output?
Object detection
59
Which additional piece of information is included with each phrase returned by an image description task of the Azure AI Vision?
Confidence score
60
When using the Face Detect API of the Azure AI Face service, which feature helps identify whether a human face has glasses or headwear?
Face attributes
61
When using the Azure AI Face service, what should you use to perform one-to-many or one-to-one face matching? Each correct answer presents a complete solution.
Face identification
Face verification
62
You are exploring solutions to improve the document search and indexing service for employees. You need an artificial intelligence (AI) search solution that will include searching text in various types of documents, such as images. Which type of AI workload is this?
Data mining
63
Which natural language processing (NLP) technique normalizes words before counting them?
Stemming
64
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?
Vectorisation
65
For which two scenarios is the Universal Language Model used by the speech-to-text API optimized? Each correct answer presents a complete solution.
Conversational
Dictation
66
Which assumption of the multiple linear regression model should be satisfied to avoid misleading predictions?
Features are independent of each other
67
You need to use Azure Machine Learning to train a regression model. What should you create in Machine Learning studio?
A job
68
[Answer choice] use plugins to provide end users with the ability to get help with common tasks from a generative AI model.
Co pilots
69
At which layer can you apply content filters to suppress prompts and responses for a responsible generative AI solution?
Safety System
70
What is the confidence score returned by the Azure AI Language detection service of natural language processing (NLP) for an unknown language name?
NaN
71
You need to identify numerical values that represent the probability of humans developing diabetes based on age and body fat percentage. Which type of machine learning model should you use?
Logistic regression - returns either a boolean value or a categorical decision
72
Which feature of the Azure AI Language service includes functionality that returns links to external websites to disambiguate terms identified in a text?
Entity recognition
73
A company deploys an online marketing campaign to social media platforms for a new product launch. The company wants to use machine learning to measure the sentiment of users on the Twitter platform who made posts in response to the campaign. Which type of machine learning is this?
Classification
74
What information do you need from your resources used for OCR?
Key and endpoint
75
True or False: The OCR method can have issues with false positives when the image is considered text-dominate
True
76
Does the Read API work synchronously or asynchronously?
Asynchronously so as to not block your application while it is reading the content and returning result to your application
77
If text analytics return a sentiment score of 1, is the sentiment positive or negative?
Positive
78
What does an acoustic model do?
Converts audio signals into phonems
79
What types of transcription does speech-to-text allow?
Real-time (application listen on microphone or other audio input source such as audio file)
Batch (audio recording from file share, remote server or azure storage)
80
How are batch transcription jobs scheduled?
On a best effort basis
81
Batch transcription should be run in an asynchronous manner
True
82
The ability to automatically detect sudden spike in a time-series data is known as
Anomaly detection
83
You are using Text Analytics to a score of NaN has been returned. What does this mean?
Not a number, the document did not contain enough text
84
Which programming languages are supported in Azure machine learning designer?
Python and R
85
You wish to develop an application which can take verbal commands. What Azure service should you provision?
Language understanding intelligent service (LUIS)
86
You are using a model to classify images and you are looking at the recall metric. What does this metric mean?
The % of the class predications made by the model that were correct
87
You are using Text Analytics to analyze a text. Which of the following is detected by the service.
Language name
A score indicating a level of confidence in the language detection
ISO 6391 language code
88
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?
Set the primary metric to R2 score
89
Does OCR API work best synchronously or asynchronously?
Synchronously
90
You wish to monitor your business’s revenue to be alerted of sudden drops In revenue. Which Azure service would you deploy?
Azure anomaly detector
91
You need to track multiple versions of a model that was trained by using Azure Machine Learning. What should you do?
Register the model
92
You have a webchat bot that provides responses from a QnA Maker knowledge base. You need to ensure that the bot uses user feedback to improve the relevance of the responses over time. What should you use?
Active learning
93
True or False: Object detection can identify multiple instances of a damaged product in an image.
False
94
True or False: You can use the Speech service to transcribe a call to text.
True
95
True or False: You can use the Text Analytics service to extract key entities from a call transcript.
True
96
True or False: You can use the Speech service to translate the audio of a call to a different language.
True
97
You want to build a personal virtual assistant. What service will you use to connect your assistant with various input channels and devices?
Azure bot services
98
You train an image classification model that achieves less than satisfactory evaluation metrics. How might you improve it?
Add more images to the training set
99
Which metric can you use to evaluate a classification model?
True positive rate
100
Predicting whether someone uses a bicycle to travel to work based on the distance from home to work is a use case for?
Classification
101
________ is the calculated probability of a correct image classification.
Accuracy
102
Ensuring that the numeric variables in the training data are on a similar scale is an example of _______.
Feature Selection
103
True or false: When creating an object detection model in the Custom Vision service, you must choose a classification type of either Multilabel or Multiclass
False
104
True or False. When creating an object detection model in the Custom Vision service, you can select from a set of predefined domains
True
105
True or False. The custom vision service can be used to analyse video files
False
106
What is scene segmentation?
Determines when a scene changes in video based on visual cues. A scene depicts a single event and it's composed by a series of consecutive shots, which are semantically related.
107
True or False: You can use the Speech service to translate the audio of a call to a different language.
True
108
True or False: The text analytics service can identify in which language text is written:
True
109
True or False: The text analytics service can detect handwritten signatures in a document.
False
110
True or False: The text analytics service can identify companies and organisations mentioned in a document.
True
111
True or False: Monitoring online service reviews for profanities is an example of natural language processing
True
112
You use Azure Machine Learning designer to publish an inference pipeline. Which two parameters should you use to access the web service? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
C. the authentication key
D. the REST endpoint
113
Which Azure resource provides direct access to both Azure AI Translator and Azure AI Speech services through a single endpoint and authentication key?
Azure AI Services
114
Which feature of the Azure AI Translator service is available only to Custom Translator?
Model training with dictionary
115
[Answer choice] can used to identify constraints and styles for the responses of a generative AI model.
System messages
116
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?
Cognitive Services
117
You plan to use the Computer Vision service to read text in a large PDF document. Which API should you use?
The Read API
118
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?
Assign Data to Clusters
119
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?
Speech
120
What is meant by seasonal data?
Data occurring at regular intervals
121
What is speech synthesis
service feature that converts text to lifelike speech.
