Question 1: 

Correct
You are working on a classification model and currently examining the values of a
confusion matrix.

Which machine learning task most appropriately describes the scenario?

model evaluation

(Correct)

model deployment

model training

feature engineering

feature selection

Explanation

examining the values of a confusion matrix - model evaluation

View the confusion matrix for the model, which is a tabulation of the predicted and actual
value counts for each possible class. For a binary classification model like this one, where
you're predicting one of two possible values, the confusion matrix is a 2x2 grid showing the
predicted and actual value counts for classes 0 and 1

https://docs.microsoft.com/en-us/learn/modules/create-classification-model-azure-
machine-learning-designer/evaluate-model

Question 2: Skipped
 An automated chat to answer questions about the price of a product, orders, refunds,
exchanges and returns is an example of _______.

conversational AI

(Correct)

computer vision

anomaly detection

knowledge mining

natural language processing

Explanation

A knowledge base of question and answer pairs - usually with some built-in natural
language processing model to enable questions that can be phrased in multiple ways to be
understood with the same semantic meaning.

A bot service that provides an interface to the knowledge base through one or more
channels.

https://docs.microsoft.com/en-us/learn/paths/explore-conversational-ai/

Question 3: Skipped
You have the below pipeline in the azure machine learning designer. What is the
output of the pipeline (at node 1)?

Larger image
 Select the most suitable option.

Data will be prepared in a normalized format

Student_Dataset_all.zip will be unzipped

(Correct)

Error: there is no such model "Unpack Zipped Datasets"

Explanation

Unpacks datasets from a zip package in user storage.

 https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-
reference/unpack-zipped-datasets

Question 4: Skipped
You have an input data-set where one column has values ranging from 0 to 1 while
another column with values ranging from 10,000 to 100,000. You plan to combine the
values of 2 columns to use it as a feature during modelling.

Which mathematical function will be applied to the data-set to rescale every feature
to the [0,1] interval linearly.

Select the best answer from below options.

Use Normalize Data module and select min-max normalizer.

(Correct)

Use Normalize Data module and select TanH normalizer.

Use the  Edit Metadata module.

Use Clip Values module and select Set of thresholds-ClipSubpeaks.

Explanation

MinMax: The min-max normalizer linearly rescales every feature to the [0,1] interval.

https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-
reference/normalize-data

Question 5: Skipped
The only way to enter data in the Azure Machine Learning designer is to use Import
data module.

Select True if the statement is correct else select False.



TRUE

FALSE

(Correct)

Explanation

Azure machine learning studio supports manually entering data through the module "Enter
Data Manually".

https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/data-
input-and-output

Question 6: Skipped
Which machine learning algorithm is mostly used for predicting the values of
categorical variables.

K-Means

Linear regression

Logistic regression

(Correct)

Explanation

Logistic Regression is used for classification problems.

 https://en.wikipedia.org/wiki/Logistic_regression#:~:text=Logistic%20regression%20is%20a
%20statistical,a%20form%20of%20binary%20regression).

Question 7: Skipped
Select two items from below list which can be dragged onto the azure machine
learning designer canvas.

pipeline

module

(Correct)

data set

(Correct)

compute

Explanation

https://docs.microsoft.com/en-us/azure/machine-learning/tutorial-designer-automobile-
price-train-score

https://docs.microsoft.com/en-us/learn/modules/create-regression-model-azure-machine-
learning-designer/create-training-pipeline

Question 8: Skipped
You have a lecture note which is sorted as text. For your exam, you need to extract
key terms from the notes to generate summaries.

Which type of AI workload should you use?



anomaly detection

conversational AI

computer vision

natural language processing

(Correct)

Explanation

Key phrase extraction is the concept of evaluating the text of a document, or documents,
and then identifying the main talking points of the document(s). Consider the restaurant
scenario discussed previously.

https://docs.microsoft.com/en-us/learn/modules/analyze-text-with-text-analytics-service/2-
get-started-azure

Question 9: Skipped
Which statements are true for computer vision? Select 2 options from below.

Predict the house price based on historical data is done by computer vision.

Computer Vision can analyze the colours and can detect the colour scheme in an image.

(Correct)


Computer Vision has the ability to identify commercial brands.

(Correct)

Extract key phrases from product reviews are done by computer vision.

Computer Vision can translate text between languages.

Explanation

In addition to these capabilities, the Computer Vision service can:

Detect image types - for example, identifying clip art images or line drawings.

Detect image color schemes - specifically, identifying the dominant foreground,

background, and overall colors in an image.

Generate thumbnails - creating small versions of images.

Moderate content - detecting images that contain adult content or depict violent, gory
scenes.

Computer Vision provides the ability to identify commercial brands. The service has an
existing database of thousands of globally recognized logos from commercial brands of
products.

https://docs.microsoft.com/en-us/learn/modules/analyze-images-computer-vision/2-
image-analysis-azure

Question 10: Skipped
You are working as a cloud consultant for a major retail company. You are planning to
create a bot from a frequently asked questions (FAQ) document. You found out that
Microsoft Azure AI has many services that can help in creating a bot seamlessly.
Which azure AI service should you use?


Text analysis

Language understanding

QnA Maker

(Correct)

Speech

Explanation

QnA Maker is a cloud-based API service that lets you create a conversational question-and-
answer layer over your existing data.

https://docs.microsoft.com/en-us/learn/modules/build-faq-chatbot-qna-maker-azure-bot-
service/2-get-started-qna-bot

Question 11: Skipped
Which of the following is/are example(s) of conversational AI workload? Choose 2
scenarios from below options.

Interactively responding to a user’s question through a website that uses a knowledge base.

(Correct)


 Assembly line machinery that independently dismantles various parts of car and places
them in a conveyor belt.

A machine that monitors the pressure of a coffee machine and automatically turns it OFF
when the pressure reaches a specific threshold.

An AI enabled smart device in the car that responds to questions such as “What is the
distance between Goldcoast and Brisbane  ?”

(Correct)

Explanation

-Interactively responding to a user’s question through a website that uses a knowledge

base.-conversational AI.

-An AI enabled smart device in the car that responds to questions such as “What will the
distance between Goldcoast and Brisbane?” conversational AI + NLP

Question 12: Skipped
Which of the following types of machine learning is NOT an example of supervised
machine learning?

Regression

Classification


 Clustering

(Correct)

Explanation

Classification and regression are supervised machine learning, clustering is unsupervised.

Clustering is an example of unsupervised machine learning, in which you train a model to

separate items into clusters based purely on their characteristics, or features. There is no
previously known cluster value (or label) from which to train the model.

https://docs.microsoft.com/en-us/learn/modules/create-clustering-model-azure-machine-
learning-designer/introduction

Question 13: Skipped
Which of the following is commonly used to predict a categorical variable?

Clustering

Anomaly detection

Linear regression

Binary or Multi-class Classification

(Correct)

Explanation

Classification is a form of machine learning that is used to predict which category, or class,
an item belongs to.

https://docs.microsoft.com/en-us/learn/modules/create-classification-model-azure-
machine-learning-designer/introduction
 Question 14: Skipped
What is the minimum number of features required to perform clustering?

(Correct)

Explanation

Clustering can be performed with one dimensional data to start with. For example clustering
people basis their age.

https://docs.microsoft.com/en-us/learn/modules/create-clustering-model-azure-machine-
learning-designer/introduction

Question 15: Skipped
You have selected the Clean Missing Data Module into the canvas and want to replace
only 80% of all the missing values present in Product_detail Dataset.csv dataset.

What parameters you should set in the Clean Missing Data module to get the required
result?

Larger image


Set Minimum missing value ratio to 20.

Set Maximum missing value ratio to 0.8

(Correct)

Set Minimum missing value ratio to 0.2.

Set Maximum missing value ratio to 80

Explanation

Maximum missing value ratio to 0.8 means that the Clean Missing data module will not
replace more than 80% of all the missing values in the dataset. The values are replaced
based on the Cleaning mode you select.
 https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/clean-
missing-data

Question 16: Skipped
For a machine learning process how should you split data for training and evaluation?

random split the data into columns for training and columns for evaluation

use feature for training and labels for evaluation

use labels for training and features for evaluation

randomly split the data into rows for training and rows for evaluation

(Correct)

Explanation

Split Rows: Use this option if you just want to divide the data into two parts. You can specify
the percentage of data to put in each split, but by default, the data is divided 50-50.

You can also randomize the selection of rows in each group, and use stratified sampling. In
stratified sampling, you must select a single column of data for which you want values to be
apportioned equally among the two result datasets.

https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/split-
data

Question 17: Skipped
You have Microsoft_Employee1 dataset having 16 rows and 4 columns. You have
another dataset Microsoft_Employee2 having 16 rows and 3 columns. You want to
combine these 2 datasets in such a way that the resultant dataset will have 16 rows
and 7 columns. You dragged these 2 datasets in the azure machine learning designer
canvas. Which module will help to achieve the desired result?


Drag the Add Rows module into the canvas and connect the output of
Microsoft_Employee1 and Microsoft_Employee2 as input.

Drag the Remove duplicate Rows module into the canvas and connect the output of
Microsoft_Employee1 and Microsoft_Employee2 as input.

Drag the Select columns in Dataset module into the canvas and connect the output of
Microsoft_Employee1 and Microsoft_Employee2 as input.

Drag the Add Columns module into the canvas and connect the output of
Microsoft_Employee1 and Microsoft_Employee2 as input.

(Correct)

Explanation

https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/add-
columns

You combine all columns from the two datasets that you specify as inputs to create a single
dataset. If you need to concatenate more than two datasets, use several instances of Add
Columns.

Question 18: Skipped
You have been tasked to build an AI solution which takes English text as input and
generates natural, reliable and expressive sounding speech that fits different
emotions in the context of various patterns of human voices like lyrical, empathy etc.

Which azure cognitive service is best suited for the above use case?


 Text-to-speech (TTS)

Language Understanding Intelligent Service

Neural TTS

(Correct)

Translator Text

Explanation

Neural Text to Speech

https://techcommunity.microsoft.com/t5/azure-ai/introducing-new-voice-styles-in-azure-
cognitive-services/ba-p/1248368

Question 19: Skipped
To interpret, the meaning of a voice message "meet me at 9 pm" which Azure AI
service will be most appropriate?

text Analytics

translator text

Speech


language understanding

(Correct)

Explanation

Ans-LUIS

On Microsoft Azure, language understanding is supported through the Language

Understanding Intelligent Service, more commonly known as Language Understanding.
To work with Language Understanding, you need to take into account three core
concepts: utterances, entities, and intents.

https://docs.microsoft.com/en-us/learn/modules/create-language-model-with-language-
understanding/1-introduction

Question 20: Skipped
Match the type of computer vision workloads to the appropriate scenarios.

To answer, select the appropriate option.

Computer Vision workloads:

-facial recognition

-image classification

-object detection

-optical character recognition

scenarios:

(1) automatically tag known friends in social media photographs

(2) digitizing historical documents

(3) locate vehicles in images

Choose the option that matches the scenarios to appropriate machine learning types.
Select one.
 (1 or 2 or 3) represents a scenario statement in the options below.

(1)image classification (2)object detection (3)optical character recognition

(1)object detection (2)object detection (3)image classification

(1)facial recognition (2)optical character recognition (3)object detection

(Correct)

(1)object detection (2)image classification (3)optical character recognition

Explanation

(1) automatically tag known friends in social media photographs - facial recognition

(2) digitizing historical documents - OCR

(3) locate vehicles in images - object detection

Question 21: Skipped
Which Microsoft guiding principle for responsible AI you should consider as most
important while developing an AI system for a self-driving car?

accountability

inclusiveness


fairness

transparency

reliability and safety

(Correct)

Explanation

To build trust, it's critical that AI systems operate reliably, safely, and consistently under
normal circumstances and in unexpected conditions. These systems should be able to
operate as they were originally designed, respond safely to unanticipated conditions, and
resist harmful manipulation. It's also important to be able to verify that these systems are
behaving as intended under actual operating conditions. How they behave and the variety
of conditions they can handle reliably and safely largely reflects the range of situations and
circumstances that developers anticipate during design and testing.

https://docs.microsoft.com/en-us/learn/modules/responsible-ai-principles/4-guiding-
principles

Question 22: Skipped
Which ML model you should use to predict the hours of overtime a service desk
person will work based on the number of Incidents received.

classification

regression

(Correct)


clustering

Explanation

Regression is a supervised machine learning technique used to predict numeric values.

Regression is a form of machine learning that is used to predict a numeric label based on an

item's features. For example, an automobile sales company might use the characteristics of
car (such as engine size, number of seats, mileage, and so on) to predict its likely selling
price. In this case, the characteristics of the car are the features, and the selling price is the
label.

https://docs.microsoft.com/en-us/learn/modules/create-regression-model-azure-machine-
learning-designer/introduction

Question 23: Skipped
While reviewing the performance metrics for a binary classification model (in the
Evaluate module of azure machine learning designer) you noted that the model has an
AUC=0.25.

What can be said about the model's performance?

The model is performing worse than random guessing.

(Correct)

The model is performing better than random guessing.

There is a 75% chance that the model will be able to distinguish between positive class and
negative class.

Explanation
 An AUC of 0.5 means the model has no discrimination capacity to distinguish between
positive class and negative class.

If the AUC for your model is higher than 0.5 for a binary classification model, then the
model performs better than a random guess.

Hence, the model is performing worse than random guessing.

https://www.analyticsvidhya.com/blog/2020/06/auc-roc-curve-machine-learning/

Question 24: Skipped
Select the most appropriate Natural Language Processing workload for below
scenario.

scenario:

Extract date/time, URLs, email addresses and phone number from the text.

Entity recognition

(Correct)

Language modelling

Speech recognition and speech synthesis

Sentiment analysis

Key phrase extraction

Explanation
 The Entity Recognition skill extracts entities of different types from text. This skill uses the
machine learning models provided by Text Analytics in Cognitive Services.

https://docs.microsoft.com/en-us/learn/modules/analyze-text-with-text-analytics-service/2-
get-started-azure

Question 25: Skipped
The ROC-AUC curve for a classification model is depicted in the image below.

Choose the best answer from below options.

Larger image

the AUC of the model is 0.


 the AUC of the model is 0.5.

the AUC of the model is infinite.

the AUC of the model is 1

(Correct)

Explanation

the AUC of the model is 1. The area under the curve is 1*1=1

https://www.analyticsvidhya.com/blog/2020/06/auc-roc-curve-machine-learning/

Question 26: Skipped
You are building an AI system for a remote proctor testing system where you need to
check if two images of a face belong to the same person.

Which facial recognition tasks will be appropriate for the above scenario.

verification

(Correct)

identification

similarity


 grouping

Explanation

Face currently supports the following functionality:

Face Detection

Face Verification

Find Similar Faces

Group faces based on similarities

Identify people

https://docs.microsoft.com/en-us/learn/modules/detect-analyze-faces/2-face-analysis-azure

Question 27: Skipped
17 images of fruits are fed to a machine learning model to identify the number of
apples. In actual, the number of apples is 12 but the model predicted 9 apples out of
which 6 are apple. The remaining 3 are bananas.

What is precision and recall  for the model?

precision is 3/12 and recall is 3/9

precision is 6/12 and recall is 6/9

precision is 6/9 and recall is 6/12

(Correct)

precision is 6/17 and recall is 9/17

Explanation
 https://en.wikipedia.org/wiki/Precision_and_recall

17 images of fruits are fed to a machine learning model to identify the number of
apples. In actual, the number of apples is 12 but the model predicted 9 apples out of
which 6 are apple. The remaining 3 are bananas.

tp = 6

fp = 3

fn = 6 (12 -6)

 = 6/(6+3)=6/9

=6/(6+6)= 6/12

Question 28: Skipped
You are using Azure Machine Learning designer to predict the price of a house.

What will be the ideal sequence of modules in Azure Machine Learning designer
pipeline?

train model --> score model --> evaluate model

(Correct)

train model --> evaluate model --> score model

score model --> train model --> evaluate model

evaluate model --> train model --> score model

 Explanation

https://docs.microsoft.com/en-us/azure/machine-learning/tutorial-designer-automobile-
price-train-score

Question 29: Skipped
Which type of machine learning should you use to predict the number of mobile
phones that will be sold next month?

Regression

(Correct)

Clustering

Classification

Explanation

Regression is a form of machine learning that is used to predict a numeric label based on an
item's features. For example, an automobile sales company might use the characteristics of
car (such as engine size, number of seats, mileage, and so on) to predict its likely selling
price.

https://docs.microsoft.com/en-us/learn/modules/create-regression-model-azure-machine-
learning-designer/introduction

Question 30: Skipped
Which of the following statement(s) is/are CORRECT? Select all that apply.

Identifying famous landmarks in an image is an example of natural language processing.



Analyse social media feeds to detect a sentiment around a political campaign is an example
of natural language processing.

(Correct)

With the help of NLP, a developer can automatically blacklist/whitelist to allow or deny
certain words in a retail website review.

(Correct)

Explanation

Identifying famous landmarks in an image is an example of natural language processing

- Computer Vision

The Text Analytics service can evaluate text and return sentiment scores and labels for each
sentence. This capability is useful for detecting positive and negative sentiment in social
media, customer reviews, discussion forums and more.

https://docs.microsoft.com/en-us/learn/modules/analyze-text-with-text-analytics-service/2-
get-started-azure

Azure Content Moderator is an AI service that lets you handle content that is
potentially offensive, risky, or otherwise undesirable. It includes the AI-powered content
moderation service which scans text, image, and videos and applies content flags
automatically, as well as the Review tool, an online moderator environment for a team of
human reviewers.

https://docs.microsoft.com/en-us/azure/cognitive-services/content-moderator/text-
moderation-api

Question 31: Skipped
Which AI service you should use to determine if a photo contains a person?

conversational AI


computer vision

(Correct)

anomaly detection

knowledge mining

natural language processing

Explanation

In Microsoft Azure, the Computer Vision cognitive service uses pre-trained models to

analyze images, enabling software developers to easily build applications that can:

Interpret an image and suggest an appropriate caption.

Suggest relevant tags that could be used to index an image.

Categorize an image.

Identify objects in an image.

Detect faces and people in an image.

Recognize celebrities and landmarks in an image.

Read text in an image.

https://docs.microsoft.com/en-us/learn/modules/analyze-images-computer-vision/1-
introduction

Question 32: Skipped
You have developed a web chatbot for a retail company and now you want to add
additional features to the bot so that it can detect how upset the customer is based on
what the customer types.
 This is an example of which type of Natural Language Processing workload?

entity recognition

keyphrase extraction

language detection

sentiment analysis

(Correct)

Explanation

The Text Analytics service can evaluate text and return sentiment scores and labels for each
sentence. This capability is useful for detecting positive and negative sentiment in social
media, customer reviews, discussion forums and more.

https://docs.microsoft.com/en-us/learn/modules/analyze-text-with-text-analytics-service/2-
get-started-azure

Question 33: Skipped
You are working on a traffic management system where you need to estimate the
distance between the cars by determining the location of cars in an image. Which
computer vision service should you choose?

image classification


 face detection

optical character recognition ocr

object detection

(Correct)

Explanation

Object detection is a form of machine learning based computer vision in which a model is
trained to recognize individual types of object in an image and to identify their location in
the image.

https://docs.microsoft.com/en-us/learn/modules/detect-objects-images-custom-vision/2-
object-detection-azure

Question 34: Skipped
You have created a training pipeline in azure machine learning designer and now you
want to experiment with the pipeline/code for which you need scalable clusters of
virtual machines. What kind of compute target is suitable for the task mentioned.

Inference Clusters

Compute Instances

Compute Clusters

(Correct)
 Explanation

Compute Instances: Development workstations that data scientists can use to work with
data and models.

Compute Clusters: Scalable clusters of virtual machines for on-demand processing of

experiment code.

Inference Clusters: Deployment targets for predictive services that use your trained models.

Attached Compute: Links to existing Azure compute resources, such as Virtual Machines or
Azure Databricks clusters.

https://docs.microsoft.com/en-us/learn/modules/use-automated-machine-learning/create-
compute

Question 35: Skipped
You are working as a solution architect for an online retail store and have been tasked
to create a service that will go through all the reviews of a product and should be able
to detect if a customer is happy with the product or upset.

Which type of AI workload should you use?

semantic segmentation

anomaly detection

regression

natural language processing

(Correct)

Explanation
 What is Sentiment analysis? Is it a part of NLP?

The Text Analytics service can evaluate text and return sentiment scores and labels for each
sentence. This capability is useful for detecting positive and negative sentiment in social
media, customer reviews, discussion forums and more.

https://docs.microsoft.com/en-us/learn/modules/analyze-text-with-text-analytics-service/

Question 36: Skipped
Which of the following can help to build an app for employees to scan and store their
expenses from a receipt

semantic segmentation

OCR

(Correct)

image classification

object detection

Explanation

The best answer of the options is OCR. In Azure for receipt reading there is a special API
called Form Recognizer which could have been a better answer. However from an
understanding perspective.

Form Recognizer is built on top of OCR which is built on top of Computer Vision

https://docs.microsoft.com/en-us/learn/modules/analyze-receipts-form-recognizer/1-
introduction

Question 37: Skipped
 While presenting at a conference, your sessions is transcribed into subtitles. This is an
example of

Text to Speech

Text Translation

Speech synthesis

Speech recognition

(Correct)

Explanation

Speech recognition means to Speech to Text. In the above example as a person speaks the
words are converted into text of the same language. Hence Speech to Text also called
Speech recognition is the right answer.

Speech recognition - the ability to detect and interpret spoken input.

Speech synthesis - the ability to generate spoken output.

https://docs.microsoft.com/en-us/learn/modules/recognize-synthesize-speech/1-
introduction

Question 38: Skipped
Choose all that is correct

You can use the Speech service to transcribe a call to text

 (Correct)

You can use text analytics service to extract key entities from a call transcript

(Correct)

You can use a speech service to translate the audio of a call to a different language

(Correct)

Explanation

All the 3 options are correct

You can use the Speech service to transcribe a call to text - Yes we can use Speech to Text
API to achieve this

https://docs.microsoft.com/en-us/learn/modules/recognize-synthesize-speech/1-
introduction

You can use a speech service to translate the audio of a call to a different language - Yes we
can use Speech translation service to achieve this

The Speech service includes the following application programming interfaces (APIs):

Speech-to-text - used to transcribe speech from an audio source to text format.

Text-to-speech - used to generate spoken audio from a text source.

Speech Translation - used to translate speech in one language to text or speech in another.

https://docs.microsoft.com/en-us/learn/modules/translate-text-with-translation-service/2-
get-started-azure

You can use text analytics service to extract key entities from a call transcript -Yes Text
Analytics API helps to achieve this

https://docs.microsoft.com/en-us/learn/modules/analyze-text-with-text-analytics-service/2-
get-started-azure

Question 39: Skipped
 You need to make the press release of your company available in multiple different
languages. Which service would you use?

LUIS

Text Analytics

Speech

Translator text

(Correct)

Explanation

Microsoft Azure provides cognitive services that support translation. Specifically, you can
use the following services:

The Translator Text service, which supports text-to-text translation.

The Speech service, which enables speech-to-text and speech-to-speech translation.

https://docs.microsoft.com/en-us/learn/modules/translate-text-with-translation-service/2-
get-started-azure

Question 40: Skipped
Which of the following can be achieved using Speech service of Azure

providing closed captions for a recorded or live videos

(Correct)


creating a transcript of a telephone call or meeting

(Correct)

an in-car system that reads text messages aloud

(Correct)

creating an automated public address system for a train station

(Correct)

Explanation

creating a transcript of a telephone call or meeting - Speech to Text

an in-car system that reads text messages aloud - Text to Speech

providing closed captions for a recorded or live videos - Speech to text

creating an automated public address system for a train station - Text to Speech

Speech to Text :The recognized words are typically converted to text, which you can use for
various purposes, such as.

- Providing closed captions for recorded or live videos

- Creating a transcript of a phone call or meeting

- Automated note dictation

- Determining intended user input for further processing

Text to Speech : You can use the output of speech synthesis for many purposes, including:
 - Generating spoken responses to user input.

- Creating voice menus for telephone systems.

- Reading email or text messages aloud in hands-free scenarios.

- Broadcasting announcements in public locations, such as railway stations or airports.

https://docs.microsoft.com/en-us/learn/modules/recognize-synthesize-speech/1-
introduction

Question 41: Skipped
Which of the following is an example of Responsible AI principle "Transparency"

Ensure that a training dataset is representative of the population

Provide documentation to help developers debug code

Enable auto scaling to ensure that a service scales based on demand

Ensure that all visuals have an associated text that can be read by a screen reader

(Correct)

Explanation

AI systems should be understandable. Users should be made fully aware of the purpose of
the system, how it works, and what limitations may be expected.

https://docs.microsoft.com/en-us/learn/modules/get-started-ai-fundamentals/7-
understand-responsible-ai

Question 42: Skipped
 When developing an AI system for self driving cars, which Microsoft principle for
Responsible AI should be applied to ensure consistent performance during
unexpected circumstances

accountability

inclusiveness

reliability and safety

(Correct)

fairness

Explanation

AI systems should perform reliably and safely. For example, consider an AI-based software
system for an autonomous vehicle; or a machine learning model that diagnoses patient
symptoms and recommends prescriptions. Unreliability in these kinds of system can result in
substantial risk to human life.

https://docs.microsoft.com/en-us/learn/modules/get-started-ai-fundamentals/7-
understand-responsible-ai

Question 43: Skipped
Which service should you use to extract text, key/value pairs, and table data
automatically from scanned documents?

Text Analytics


Form Recognizer

(Correct)

Ink Recognizer

Custom Vision

Explanation

The Form Recognizer in Azure provides intelligent form processing capabilities that you
can use to automate the processing of data in documents such as forms, invoices, and
receipts. It combines state-of-the-art optical character recognition (OCR) with predictive
models that can interpret form data by:

Matching field names to values.

Processing tables of data.

Identifying specific types of field, such as dates, telephone numbers, addresses, totals, and
others.

https://docs.microsoft.com/en-us/learn/modules/analyze-receipts-form-recognizer/2-
receipts-azure

Question 44: Skipped
Match the machine learning tasks to the appropriate scenarios.

1. Examine the values of a confusion matrix

2. Splitting a date into date, month and year fields

3. Picking temperature and pressure to train a model

1. Examine the values of a confusion matrix - Model Training

 2. Splitting a date into date, month and year fields -  Feature Engineering
3. Picking temperature and pressure to train a model -  Feature Evaluation

1. Examine the values of a confusion matrix - Model Evaluation

2. Splitting a date into date, month and year fields -  Feature Selection
3. Picking temperature and pressure to train a model -  Feature Evaluation

1. Examine the values of a confusion matrix - Model Evaluation

2. Splitting a date into date, month and year fields -  Feature Engineering
3. Picking temperature and pressure to train a model -  Feature Evaluation

(Correct)

Explanation

1. Examine the values of a confusion matrix - Model Evaluation

2. Splitting a date into date, month and year fields -  Feature Engineering

3. Picking temperature and pressure to train a model -  Feature Evaluation

Question 45: Skipped
Match the types of computer vision to the appropriate scenarios.

Identify celebrities in Images

Extract movie names from movie poster

locate vehicles in an image

Identify celebrities in Images - Facial Recognition

Extract movie names from movie poster - OCR
locate vehicles in an image -  Image classification

Identify celebrities in Images - Facial Recognition

 Extract movie names from movie poster - OCR
locate vehicles in an image -  Object detection

(Correct)

Identify celebrities in Images - Image Classification

Extract movie names from movie poster - OCR
locate vehicles in an image -  Object detection

Explanation

Identify celebrities in Images - Facial Recognition

Extract movie names from movie poster - OCR

locate vehicles in an image -  Object detection