VASAVI JNANA PEETHA EVENING COLLEGE

ARTIFICIAL INTELLIGENCE
UNIT-1 Introduction to AI on Azure
1)Define/What is AI.
Artificial intelligence (AI) is the creation of software that imitates human behaviour and
capabilities.
Examples: fraud detection, spam filtering, malware threat detection, business process
automation, medical diagnosis, image processing, prediction, classification, learning
association, regression etc.

2)Define/what is Azure AI.

Azure AI is a portfolio of AI services designed for developers and data scientists.

3)Define computer Vision.

Computer vision is the area of AI that deals with visual processing. It is a service which
enables software engineers to create intelligent solutions that extract information from
images.

4)Define Natural Language Processing.

Natural Language Processing (NLP) is the area of AI that deals with creating software
that understands written and spoken language.

5)Define Knowledge Mining.

It is the capability to extract information from large volumes of unstructured data to
create a knowledge store.

6)What are the Azure machine learning features and capabilities?

Features and its capabilities:
 Automated machine learning: This feature enables non-experts to quickly create
aneffective machine learning model from data.
 Azure Machine Learning designer: A graphical interface enabling no-
codedevelopment of machine learning solutions.
 Data and compute management: Cloud-based data storage and compute services
thatprofessional data scientists can use.
 Pipelines: Data scientists, software engineers and IT operations professionals can
definepipelines.

7)Explain Computer vision tasks.

Task1: Image Classification: It involves training a machine learning model to classify
images based on their contents.
Example: In traffic monitoring solution we use image classification model to classify
images based on type of vehicle such as taxis, buses and cyclists.
Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 1
Task2: Object detection: These machine learning models are trained to classify
individual objects within an image, and identify their location with a bounding box.
Example, a traffic monitoring solution might use object detection to identify the
location of different classes of vehicle.
Task3: Semantic Segmentation: It is a machine learning technique in which individual
pixels in the image are classified according to the object.
Example: A traffic monitoring solution might overlay traffic images with mask layers to
highlight different vehicles.
Task 4: Image Analysis: create solutions that combine machine learning models with
advanced image analysis techniques to extract information from images.
Task 5: Face Detection, Analysis and Recognition: It is a specialized form of object
detection that locates human faces in an image.
It can be combined with classification and facial geometry analysis to recognise
individuals.
Task 6: Optical Character Recognition(OCR): It is a technique used to detect and readtext
in image.
You can use OCR to read text in paragraphs or to extract information from scanned
documents.

8)List and explain Computer vision service and capabilities or cognitive services
azure provides.
Services and Capabilities:
Computer vision: Use this service to analyze images and video and extract description
tags.
Custom Vision: Use this service to train image classification and object detection model.
Face: It enables you to build face detection and facial recognition solutions.
Form Recogniser: Use this service to extract information from scanned forms and
invoices.

9)What are NLP services in Microsoft Azure?Explain?

Natural Language Processing (NLP) is the area of AI that deals with creating software
that understands written and spoken language.
NLP services in Microsoft Azure are
(i)Text Analytics: Use this service to analyze text documents and extract key phrases, detect
entities (such as places, dates, and people), and evaluate sentiment (how positive ornegative a
document is).
(ii)Translator Text: Use this service to translate text between more than 60 languages.
(iii)Speech: Use this service to recognize and synthesize speech, and to translate spoken
languages.
(iv)Language Understanding Intelligent Service (LUIS): Use this service to train a
language model that can understand spoken or text-based commands.

Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 2
10)Explain the steps to configure Tune Model Hyperparameters?
 Add the Tune model Hyperparameters component to your pipeline in the designer.
 Connect an untrained model to the leftmost input.
 Add the dataset that you want to use for training and connect it to the middle input
ofTune Model Hyperparameters.
 In the right panel of tune model hyperparameters,choose a value for parameter
sweeping mode,It controls how parameters are selected.
Entire grid:It is useful when you don’t know what is the best parameter settings
might be.
Random sweep:The component will randomly select parameter values over a
system-defined range.
 For Label Column selector to choose a single label column.
 Choose the number of runs:
Maximum number of runs on random sweep: If you choose a random sweep
youcan specify how many times the model should be trained.
 For, Ranking choose a single metric to use for ranking the models.
 For Random seed, enter an integer number as a pseudo random number generator
stateused for randomly selecting parameter values over a pre-defined range.
 Submit the pipeline.

11)Define neural network.

The basic unit of the brain is known as neuron. When a large number of neurons are
present together to give out a large number of outputs it forms a neural layer. These
multiple layers combine to form a neural network.

12)Explain Artificial Intelligence Workloads?

There are basic 6 AI Workloads
i)Predicting and Forecasting: It can have a large scale of impact in our current day
world with power of accuracy it holds.
Example: Weather forecasting systems: AI model will be provided an abundant amount
of data of weather conditions to predict weather changes and long term climate impact.
ii)Anomaly Detection: It is using machines to observe and find the unexpected value,
within an already established range of values.
Example: Smart Watches
iii)Computer Vision: It analyzes videos and images to extract specific information. The
information may be images, video or subject of matter in an image.
It involves a model being trained with thousand of pictures labels videos and keycontents
to be able to recognize and classify images.
Example : Every time safe search is run when surfing on google.
iv)Natural Language Processing(NLP):It is a tool for machines to be able to
communicate in human languages as well as convert speech to text and vice versa.
It allows computers to understand questions, requests and commands as well asrespond
to them.
Example:Siri
Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 3
v)Knowledge Mining: It is process where computers and machines extract specific
valuable data from unstructured files or ontent.
There are three basic steps:
Step1: Pull the data simple process of pulling out the specified data.
Step2:Use the appropriate cognitive service to extract value from gathered data.
Step3: analysis of data through exploration.
vi)Conversational AI: It allows simple AI solutions to be able to converse and talk with
humans.
Chatbots: can be used for things like customer support, making appointments.

13)Is there any service for Anomaly detection from Microsoft Azure?
The Anomaly Detector service provides an application programming interface (API)that
developers can use to create anomaly detection solutions.

14)What are the Conversational AI services in Microsoft Azure?

QnA Maker: This cognitive service enables you to quickly build a knowledge base of
questions and answers that can form the basis of a dialog between a human and an AI
agent
Azure Bot Service: This service provides a platform for creating, publishing, and managing
bots. Developers can use the Bot Framework to create a bot and manage it withAzure Bot
Service - integrating back-end services like QnA Maker and LUIS, and connecting to
channels for web chat, email, Microsoft Teams, and others.

15)What is responsible AI?

 Artificial Intelligence is a powerful tool that can be used to greatly benefit the world.
However, like any tool, it must be used responsibly.
 At Microsoft, AI software development is guided by a set of six principles, designed
to ensure that AI applicationsprovide amazing solutions to difficult problems
without any unintended negative consequences.

16)What are the six guiding principles of responsible AI?

 Fairness: AI systems should treat all people fairly.
For example, suppose you create a machine learning model to support a loan approval
application for a bank.The model should make predictions of whether or not the loan
should be approved without incorporating any bias based on gender, ethnicity, or other
factors that might result in an unfair advantage or disadvantage to specific groups of
applicants.
 Reliability and safety: AI systems should perform reliably and safely.
For example, consider an AI-based software system for an autonomous vehicle; or
amachine learning model that diagnoses patient symptoms and recommends
prescriptions. Unreliability in these kinds of system can result in substantial riskto
human life.
 Privacy and security: AI systems should be secure and respect privacy. The machine
Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 4
 learning models on which AI systems are based rely on large volumes of data, which
may contain personal details that must be kept private. Even after themodels are
trained and the system is in production, it uses new data to make predictions or take
action that may be subject to privacy or security concerns.
 Inclusiveness: AI systems should empower everyone and engage people.AI should
bring benefits to all parts of society, regardless of physical ability, gender,sexual
orientation, ethnicity, or other factors.
 Transparency: 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.
 Accountability: People should be accountable for AI systems. Designers and
developers of AI-based solution should work within a framework of governanceand
organizational principles that ensure the solution meets ethical and legal standards
that are clearly defined.

17)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?
Ans:Computer Vision

18)What are the various kinds of machine learning models?

i)Regression (supervised machine learning): We use historic data to train the model to
predict the numerical value.
ii)Classification (supervised machine learning): We can fit the features into the model
and predict the classification of the label
iii)Unsupervised Machine learning: You don't have a label to predict. you only have
features. You have to create clusters based on the features.

19)What is the process of machine learning regardless of the model?

i)Data Ingestion: Youneed to get the data to train your model.
ii)Data Pre-processing: Identify the features that help the model to predict and
discarding others
iii)Data Cleaning: Fix any errors or removing the items which has errors.
iv)Replacing Feature Values: Find the replacement feature values if any missing. Inthis
process you might use existing feature engineering to find the value.
v)Apply Algorithms: Apply algorithms on this data for the processing until you arehappy
with the model predictions.
vi)Deploy Model: Finally you deploy your model into machine learning service sothat
applications can connect to it.

20)What are the settings you need when creating a Machine learning workspace?
Workspace Name: A unique name of your choice.
Subscription: Your Azure subscription.
Resource group: Create a new resource group with a unique name.
Location: Choose any available location.

Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 5
Workspace edition: Enterprise

21)How many kinds of Compute resources that data scientists can use to train their
models?
i)Compute Instances: Development workstations that data scientists can use to work with
data and models.
ii)Compute Clusters: Scalable clusters of virtual machines for on-demand processing of
experiment code.
iii)Inference Clusters: Deployment targets for predictive services that use your trained
models.
iv)Attached Compute: Links to existing Azure compute resources, such asVirtual
Machines or Azure Data bricks clusters.

22)What can Computer Vision cognitive service do?

 Interpret an image and suggest an appropriate caption.
 Suggest relevant tags that couldbe 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.

23)When using Computer Vision, what is the difference between Computer Vision
andCognitive Services?
Computer Vision: A specific resource for the Computer Vision service. Use this resource
type if you don’t intend to use any other cognitive services, or if you want to track utilization
and costs for your Computer Vision resource separately.
Cognitive Services: A general cognitive services resource that includes Computer Vision
along with many other cognitive services; such as Text Analytics, Translator Text, and
others. Use this resource type if you plan to use multiple cognitive services and want to
simplify administration and development.

24)What is Text Analytics?

Text analytics is a process where an artificial intelligence (AI) algorithm, running on a
computer, evaluates these same attributes in text, to determine specific insights.

25)What is Speech recognition?

The ability to detect and interpret spoken input. Speech recognition is concerned with
taking the spoken word and converting it into data that can be processed - often by
transcribing it into a text representation. The spoken words can be in the form of a
recorded voice in an audio file, or live audio from a microphone.

Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 6
26)What is Speech synthesis?
The ability to generate spoken output. Speech synthesis is in many respects the reverse of
speech recognition. It is concerned with vocalizing data, usually by converting text to speech

27)What are the services for speech recognition and speech synthesis from
Azure?
 The Speech-to-Text API
 The Text-to-Speech API

28)Write abbreviations of AI and ML

AI -Artificial Intelligence
ML -Machine Learning

29)What is Artificial Intelligence? Give some examples.

Artificial Intelligence is the branch of computer science concerned with the
study of simulating human intelligence processes by machines, especially
computers so that the machine can behave, think as well make decisions like a
human.
Or
AI is techniques that help machines and computers mimic human behaviour.
Examples: Maps and Navigation, Facial Detection and Recognition, Text Editors or
Autocorrect, Chatbots, Digital Assistants, Social Media, E-Payments

30)What is Machine Learning? Give real time examples.

Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications
to become more accurate at predicting outcomes without being explicitly programmed to do so.
Machine learning algorithms use historical data as input to predict new output values.

31)What are the applications of Artificial Intelligence?

a. AI in Astronomy
 Artificial Intelligence can be very useful to solve complex universe
problems.
 AI technology can be helpful for understanding the universe such as how it works,
origin, etc.
b. AI in Healthcare
 Healthcare Industries are applying AI to make a better and faster diagnosis than
humans.
 AI can help doctors with diagnoses and can inform when patients are worsening so that
medical help can reach to the patient before hospitalization.
c. AI in Gaming
 AI can be used for gaming purpose.
 The AI machines can play strategic games like chess, where the machine needs to think
of a large number of possible places.
Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 7
d. AI in Finance
 AI and finance industries are the best matches for each other.
 The finance industry is implementing automation, chatbot, adaptive intelligence,
algorithm trading, and machine learning into financial processes.
e. AI in Data Security
 AI can be used to make your data more safe and secure.
 Some examples such as AEG bot, AI2 Platform,are used to determine software bug and
cyber-attacks in a better way.
f. AI in Social Media
Social Media sites such as Facebook, Twitter, and Snapchat contain billions
of user profiles, which need to be stored and managed in a very efficient way.
g. AI in Automotive Industry
 Some Automotive industries are using AI to provide virtual assistant to their user for
better performance.
 Such as Tesla has introduced TeslaBot, an intelligent virtual assistant.
h. AI in Robotics:
 Artificial Intelligence has a remarkable role in Robotics.
 Usually, general robots are programmed such that they can perform some repetitive
task, but with the help of AI, we can create intelligent robots which can perform tasks
with their own experiences without pre-programmed.
 Humanoid robot named as Erica and Sophia has been developed which can talk and
behave like humans.
i. AI in Entertainment
 We are currently using some AI based applications in our daily life with some
entertainment services such as Netflix or Amazon.
 With the help of ML/AI algorithms, these services show the recommendations for
programs or shows.
j. AI in E-commerce
 AI is providing a competitive edge to the e-commerce industry, and it is becoming more
demanding in the e-commerce business.
 AI is helping shoppers to discover associated products with recommended size, color,
or even brand.
k. AI in education:
 AI can automate grading so that the tutor can have more time to teach.
 AI chatbot can communicate with students as a teaching assistant.

32)What are the applications of Machine Learning?

i)Image Recognition:
 Image recognition is one of the most common applications of machine learning. It is
used to identify objects, persons, places, digital images, etc.
 The popular use case of image recognition and face detection is, Automatic friend
tagging suggestion

Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 8
ii)Speech Recognition
While using Google, we get an option of "Search by voice," it comes under
speech recognition, and it's a popular application of machine learning.
iii)Traffic prediction:
If we want to visit a new place, we take help of Google Maps, which shows
us the correct path with the shortest route and predicts the traffic conditions.
iv)Product recommendations:
Machine learning is widely used by various e-commerce and entertainment companies such
as Amazon, Netflix, etc., for product recommendation to the user.
v)Self-driving cars:
 One of the most exciting applications of machine learning is self-driving cars. Machine
learning plays a significant role in self-driving cars.
 Tesla, the most popular car manufacturing company is working on self-driving car.
vi)Virtual Personal Assistant:
 We have various virtual personal assistants such as Google assistant,
Cortana, Siri. As the name suggests, they help us in finding the information using our
voice instruction.
 These assistants can help us in various ways just by our voice instructions such as Play
music, call someone, Open an email, Scheduling an appointment, etc.
vii)Medical Diagnosis:
 In medical science, machine learning is used for diseases diagnoses.
 With this, medical technology is growing very fast and able to build 3D models that can
predict the exact position of lesions in the brain.

33)What is Conversational AI?Explain Chat bot?

Conversational AI:
 It allows simple AI solutions to be able to converse and talk withhumans.
 The capability of a software "agent" to participate in a conversation.

Chatbots:
 It can be used for things like customer support, making appointments.
 A chatbot in AI is a program that is capable of generating written or spoken content
from a user's input prompt and simulating a human-like conversation.
 A chatbot is a software application that aims to mimic human conversation through text
or voice interaction.
 Modern chatbots are artificial intelligence (AI) systems that are capable of maintaining
a conversation with a user in natural language and simulating the way a human would
behave as a conversational partner.
 Such technologies often utilize aspects of deep learning and natural language
processing.

34.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

Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 9
measurements. Which Azure service should you use?
Ans:Azure Machine Learning

35)How Machine Learning Works?Explain with the help of a flowchart?

 Machine Learning is an AI technique that teaches computers to learn from
experience.
 Machine learning algorithms use computational methods to “learn” information directly
from data without relying on a predetermined equation as a model.
 The algorithms adaptively improve their performance as the number of samples
available for learning increases.

Flow chart

it has emergence from Computer Science as the core subject. Artificial Intelligence has one
main sub-branch known as Data Science. It splits into four subfields:
 Data Mining
 Data Analytics
 Big Data
 Machine Learning (ML)
The chart shows us that Data is the main dependency of AI. Without any data or information,
we cannot do anything. It needs to be present in raw format for analysis and processing.
Maintaining all other factors we also see that all the four sub-fields of Data Science have
a core dependency among themselves.

Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 10
36)How does the anomaly detector service evaluate real time data for anomalies?
Anomaly Detector is an AI service with a set of APIs, which enables you to monitor and detect
anomalies in your time series data with little machine learning (ML) knowledge, either batch
validation or real-time inference.

37)What is Azure Automated machine learning?

It is a feature enables non-experts to quickly create aneffective machine learning model
from data.

38)Define data.Give an example.

Data is a collection raw facts.
Example student regno,class,combination fees

39)What does data granularity mean?

 Data granularity is the lowest level of detail that's available within a data collection.
 Data Granularity refers to the level of detail or precision of the data.

Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 11
 ALL THE BEST

Yogesha S N
B.Sc B.ed MCA M.Sc
Vasavi Jnana Peetha Evening College Page 12