ARTIFICIAL INTELLIGENCE

QUESTION BANK – CLASS 10

CHAPTER 1: INTRODUCTION TO AI: FOUNDATIONAL CONCEPTS
One (01) Mark Questions
Fill in the Blanks:

1. The basis of decision making depends upon the availability of and how we
experience and understand it. (information/data/conditions/past experience/
knowledge/awareness.)
2. A machine can also become intelligent if it is trained with which helps them
achieve their tasks (data)

True/False:
1. A machine is artificially intelligent when it can accomplish tasks by itself. (True)
2. Is a smart washing machine an example of an Artificially Intelligent devices? (False)
3. Platforms like Netflix, Amazon, Spotify, YouTube etc. show us recommendations on the
basis of what we like. (True)

Direct Question:

1. Define Artificial Intelligence.

A machine is artificially intelligent when it can accomplish tasks by itself - collect data,
understand it, analyze it, learn from it, and improve it.
OR
When a machine possesses the ability to mimic human traits, i.e., make decisions,
predict the future, learn and improve on its own, it is said to have artificial intelligence.
OR
Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a
software think intelligently, in a similar manner to how intelligent humans think.
OR
AI is a form of intelligence; a type of technology and a field of study. AI theory and
development of computer systems (both machines and software) are able to perform
tasks that normally require human intelligence.
OR
Artificial Intelligence works to implement human intelligence in machines: creating
systems that understand, think, learn, and behave like humans.
OR
Artificial Intelligence or AI for short, refers to any technique that enables computers to
mimic human intelligence. An artificially intelligent machine works on algorithms and data
fed to it and gives the desired output.
 Two (02) Mark Questions

1. Mention four examples of artificially intelligent applications in our

smartphones.
Phone Smart Lock / Snapchat filter / Shopping websites / Netflix / YouTube / Face
Detection / Google Maps / Emotions recognition / Google assistant / Natural language
recognition / image detection / beauty filters etc. (2 marks for any four right
examples)
2. Mention four examples of machines that are not AI but confused with AI.
Automatic gates in shopping malls / remote control drones/ a fully automatic washing
machine/ Air Conditioner/ Refrigerator/ Robotic toy cars/ Television etc.

3. Pick the odd one out and justify your answer:

a. Snap Chat Filter b. Face Lock in Phone
c. Chatbot d. Image search Option
Ans: Chatbot (1 marks), as it is NLP based, the other three are Computer vision based
(1marks for justification).

4. Explain how AI works in the following areas (any two):

a. Google Search Engine b. Voice Assistants c. E-commerce websites

a. Google Search Engine:

With the help of AI, Google Search Engine has been turned into Intelligent search
which is a new network of systems that produces direct answers. It uses voice and
image searches and has incorporated deep learning to fasten the searches with more
accuracy.
b. Voice assistant:
AI is being used in voice assistants to recognize words spoken by the user. NLP has
capabilities like “Speech-to-Text” convert the natural language of the user into text for
further processing. As the digital assistant answers more and more queries, it “learns”
using ML algorithms. The more tasks it performs, its ML algorithms help it “learn”
from the tasks and the preferences of the user. As a result, the digital assistant
improves its performance over time.
c. E-commerce website:
With the use of big data, AI in E-Commerce is impacting customer choices by recording
the data of previous purchases, searched products, and online browsing habits.
Product recommendations provide multiple benefits for E-commerce retailers
including: Higher number of returning customers.
5. How has AI changed the gaming world?
AI has changed the world of gaming by making the game more intelligent by providing
them the ability to learn using machine learning algorithms. Games these days try to
understand human patterns and give responses on the basis of it and also give new
difficulty levels
OR
AI has changed the gaming world in terms of feel and emotions. Some video games
react to player skill level. Depending on how well you do, adaptive AI ratchets the
game’s difficulty level up and down to give you a greater challenge when you need it or
to prevent you from rage-quitting in frustration. AI can also adapt to your playing style
by making the game more exciting.
 4 Mark Questions

1. What is Intelligence? Explain in brief any three types of intelligence that are
mainly perceived by human beings?
Intelligence is the ‘ability to perceive or infer information, and to retain it as knowledge
to be applied towards adaptive behavior within an environment or context.’
OR
Intelligence is the ability to interact with the world (speech, vision, motion,
manipulation), ability to model the world and to reason about it, ability to learn, ability
to make decisions and to adapt.
OR
Intelligence has been defined in many ways: It involves abstract reasoning, mental
representation, problem solving, and decision making, the ability to learn, emotional
knowledge, creativity, and adaptation to meet the demands of the environment
effectively.

As per major researches, there are mainly 9 types of Intelligence;

(i) Mathematical Logical Intelligence: A person's ability to regulate, measure,
and understand numerical symbols, abstraction and logic
(ii) Linguistic Intelligence: Language processing skills both in terms of
understanding orimplementation in writing or speech.
(iii) Spatial Visual Intelligence: It is defined as the ability to perceive the visual
world and the relationship of one object to another.
(iv) Kinesthetic Intelligence: Ability that is related to how a person uses his limbs
in a skilled manner.
(v) Musical Intelligence: As the name suggests, this intelligence is about a
person's ability to recognize and create sounds, rhythms, and sound patterns
(vi) Intrapersonal Intelligence: Describes the level of self-awareness someone has
starting from realizing weakness, strength, to recognizing his own feelings
(vii) Existential Intelligence: An additional category of intelligence relating to
religious andspiritual awareness.
(viii) Naturalist Intelligence: An additional category of intelligence relating to the
ability to process information on the environment around us.
(ix) Interpersonal Intelligence: Interpersonal intelligence is the ability to
communicate with others by understanding other people's feelings and the
influence of the person.
2. Read the given scenario and answer the questions that follow:
A farmer keeps rabbits in three large hutches that stand in a row in his backyard.
Each of the hutches is painted different colours – red, yellow and green. Until
recently, the number of rabbits in the green hutch was twice as large as the
number of rabbits in the yellow hutch. Then, one day, the farmer took five rabbits
out of the left-side hutch and gave them away to the local school’s pet corner. He
also took half of the rabbits that remained in the left-side hutch and moved them
to the red hutch.
a. What was the colour of the left-side hutch? Justify your answer with
explanation.
 The answer is yellow.
Explanation: As we already know at the outset the number of rabbits in the green
hutch was twice as large as the number of rabbits in the yellow hutch. This means that
the number of rabbits in the green hutch was an even number. After the farmer
removed five rabbits from the left side hutch, then the number of rabbits that
remained there also became an even number. This is proven by the fact that it was
divisible by 2. Therefore, before those five were removed, the left side hutch contained
an uneven number of rabbits hence the left side hutch cannot be the green one, but
based on the given information, it cannot be the red one. Hence it is yellow.

3. Differentiate between what is AI and what is not AI with the help of an example?
AI Machine Not AI machine
1. AI machines are trained with data 1. Smart machines which are not AI, do
and algorithm. not require training data, they work on
2. AI machines learn from mistakes and algorithms only.
experience. They try to improvise on 2. Smart machines work on fixed
their next iterations. algorithms and they always work with
3. AI machines can analyses the the same level of efficiency, which is
situation and can take decisions programmed into them.
3. Machines which are not AI cannot take
4. AI based drones capture the real-time
decisions on their own.
data during the flight, processes it in
real-time, and makes a human- 4. An automatic door in a shopping mall,
independent decision based on the seems to be AI-enabled, but it is built
processed data. with only sensor technology.
(Any other valid examples of AI and Non-AI machine can be considered.)

While we see a lot of AI applications around us, there still exist a lot of them which are
smart but not intelligent.
An AI enabled machine should not only recognize, but should also do something with
its gathered information. Artificial intelligence” must mean a human-made interface
with the power to reason and integrate knowledge. AI must demonstrate at least some
of the following behaviors associated with human intelligence: planning, learning,
reasoning, problem solving, knowledge representation, perception, motion,
manipulation and, to a lesser extent, social intelligence, and creativity.
Most IOT items are ordinary things outfitted with sensors and connected to the
Internet. For example, sensors in your office can recognize shadows or movements,
but that doesn’t make them an example of artificial intelligence. A fully automatic
washing machine can work on its own, but it requires human intervention to select the
parameters of washing and to do the necessary preparation for it to function correctly
before each wash, which makes it an example of automation, not AI

4. A scenario is given to you below. Read it and answer the questions that follow:
Late one night, a car ran over a pedestrian in a narrow by street and drove away
without stopping. A policeman who saw the vehicle leave the scene of the accident
reported it moving at very high speed. The accident itself was witnessed by six
bystanders. They provided the following conflicting accounts of what had
happened:
 - It was a blue car driven by a man;
- The car was moving at high speed and its headlights were turned off;
- The car did have license plates; it wasn’t going very fast;
- It was a Toyota and its headlights were turned off;
- The car didn’t have license plates; the driver was a woman;
- It was a grey Ford.
When the car and its driver were finally apprehended, it turned out that only one
of the six eyewitnesses gave a fully correct description. Each of the other five
provided one true and one false piece of information. Keeping that in mind, can
you determine the following:

a. What was the car’s brand? Ans: FORD

b. What was the colour of the car? Ans: BLUE
c. Was the car going fast or slow? Ans: FAST
d. Did it have license plates? Ans: NO
e. Were its headlights turned on? Ans: NO
f. Was the driver a man or a woman? Ans: WOMAN

Explanation: Out of the statements of 6 bystanders, the third statement becomes false
as the policeman who saw the vehicle leave the scene of the accident reported it
moving at very high speed. Then eliminating all false statements of bystanders, the
above results can be extracted.
5. How intelligent robots are helping us in accomplishing dangerous jobs?
Robots let humans avoid some hurtful work:
(i) Lifting up heavy material at the construction site.
(ii) Stirring and mixing metals or liquids at a high temperature.
(iii) Collecting and packaging of radioactive waste.
(iv) Working in contaminated and dusty environments.

CHAPTER 2: INTRODUCTION TO AI: BASICS OF AI

One (01) Mark Questions
Fill in the blanks:
1. One of the major sources of data for many major companies is the device which all of us
have in our hands all the time (Smartphone/ Mobile Phones)
2. The world of Artificial Intelligence revolves around (Data)

True/False:
3. All the apps collect some kind of data. (True)

Direct Questions:
4. What do you understand by Machine Learning?
Machine learning focuses on the development of computer programs that can access data
and use it to learn for themselves.
5. What do you understand by Deep Learning?
Deep learning is an artificial intelligence (AI) function that imitates the workings of the
human brain in processing data and creating patterns for use in decision making.
6. What are the three domains of AI?
● Data Science/ Big Data
● Computer Vision
● Natural Language Processing (NLP)

7. Name any two examples of Data science?

(Any two out of the following)
Price Comparison Websites/ Website Recommendations/ Fraud and Risk detection/
Internet search/ Personalized healthcare recommendations / Optimizing Traffic routes
in real-time / image tagging.

8. Name any two examples of Computer vision?

(Any two out of the following)
Self-Driving cars/ Autonomous vehicles Face Lock in Smartphones/ MedicalImaging/
Facial recognition /Security Systems / Waste Management / Satellite imaging.

9. Name any two examples of Natural Language Processing?

(Any two out of the following)Email filters/Smart assistants/ Sentiment
Analysis/Automatic Summarization/Search results / Language translation / Digital phone
calls.
Two (02) Mark Questions
1. What is Data science? Give an example of it.
Data sciences is a domain of AI related to data systems and processes, in which the system
collects numerous data, maintains data sets and derives meaning/sense out of them. The
information extracted through data science can be used to make a decision about it.
For example: a company that has petabytes (1024 Terabytes) of user data may use data
science to develop effective ways to store, manage, and analyze the data.

2. What is Computer Vision? Give an example of it.

Computer Vision, abbreviated as CV, is a domain of AI that depicts the capability of a
machine to get and analyze visual information and afterwards predict some decisions about
it. The entire process involves image acquiring, screening, analyzing, identifying and
extracting information.
For Example: - Self-Driving cars/ Automatic Cars, Face Lock in Smartphones

3. What is Natural Language Processing? Give an example of it.

In NLP, we teach machines how to understand and communicate in human language.
Natural language refers to speech analysis in both audible speeches, as well as text of a
language. NLP systems capture meaning from an input of words (sentences, paragraphs,
pages, etc.)
For Example: Email filters, Smart assistants: - Apple’s Siri and Amazon’s Alexa
4. Where do we collect data from?
Data can be collected from various sources like –
 Surveys
 Sensors
 Observations
 Web scrapping (Internet)
 Interviews
 Documents and records.
 Oral histories
5. Why do we need to collect data?
Data to a machine is similar to food for human being to function. The world of Artificial
Intelligence revolves around Data. Every company whether small or big is collecting data
from as many sources as possible. Data is called the New Gold today. It is through data
collection that a business or management has the quality information they need to make
informed decisions from further analysis, study, and research. Data collection allows them
to stay on top of trends, provide answers to problems, and analyze new insights to great
effect.
Three (03) Mark Questions

1. What do you understand by AI, ML & DL? How are they different from each
other?

a) Artificial Intelligence (AI)

AI is incorporating human intelligence to machines. Whenever a machine completes
tasks based on a set of rules that solve problems (algorithms), such an “intelligent”
behavior is what is called artificial intelligence.

b) Machine Learning (ML)

ML is a subset of AI that uses statistical learning algorithms to build smart systems. The
ML systems can automatically learn and improve without explicitly being programmed.

c) Deep Learning (DL)

In Deep Learning, the machine is trained with huge amounts of data which helps it in
training itself around the data. Such machines are intelligent enough to develop
algorithms for themselves.

How they differ?

 Deep Learning is the most advanced form of Artificial Intelligence out of these three. Then
comes Machine Learning which is intermediately intelligent and Artificial intelligence
covers all the concepts and algorithms which, in some way or the other mimic human
intelligence.
  Therefore, AI is the umbrella term which covers ML and DL.

2. Why do apps collect data in our phone?

One of the major sources of data for many major companies is the device which all of us have
in our hands all the time: Smartphones. Smartphones have nowadays become an integral
part of our lives. Most of us use smartphones more than we interact with people around us.
For the facilities that smartphones provide us, Apps need a lot of data which is collected
from the user like details about your face, browsing history, or your geographic location,
contact list etc. This data is collected with user’s consent which he/she gives at the time of
installing an app by clicking on “yes” or “allow” options which clearly means that we
ourselves are giving permissions to the Apps.
Permissions by themselves are harmless and even useful to provide users a good mobile
experience.
This data is collected to provide us with a lot of facilities and features which have made our
lives easier. Another reason to collect the data is to provide us with customized
recommendations and notifications according to our choices.
One more reason to collect the data is to make their app more accurate and efficient.

3. Should AI replace laborious jobs? Is there an alternative for major unemployment?

Yes, AI should replace laborious jobs.

● AI can replace laborious jobs like lifting of heavy items, working in mines etc.
● AI can indeed automate most repetitive and physical tasks.
● In future, AI would be a good option in the field of architecture and construction.
OR
No, AI should not replace laborious jobs completely as if it replaces laborious jobs
completely, then there will be no source of income for the daily wage workers due to
unemployment. So, industry owners can use some machines but more of man power. Hence
the production will not get affected as humans are smarter than machines since they were
the ones who invented AI.
Note: As this is an open-ended question so both the answers (yes/No) are correct but it
must be with correct justification.

Is there an alternative for major unemployment?

● AI taking over laborious jobs won’t create unemployment. It is just a groundless fear.
The standard view of technical change is that some jobs are displaced by the
substitution of machines for labour, but that the fear of total displacement is misplaced
because new jobs are created, largely due to the technology-fuelled increase in
productivity. Humans have always shifted away from work suitable for machines and to
other jobs.
● The basic fact is that technology eliminates jobs, not work. If this level of AI revolution
will happen, lots of job opportunities will be created. For example: 20-30 years ago,
being an accountant was a lucrative job, but AI took over this job but this created a lot
of opportunities, it raised the demand of a software engineer, data scientist, etc.
● It will open doors to skillful jobs rather than doing laborious tasks.
● Thus, we will be able to cope with the level of major unemployment, if AI took over
laborious jobs.
4. As Artificially Intelligent machines become more and more powerful, their ability to
accomplish tedious tasks is becoming better. Hence, it is now that AI machines have
started replacing humans in factories. While people see it in a negative way and say AI
has the power to bring mass unemployment and one day, machines would enslave
humans, on the other hand, other people say that machines are meant to ease our lives.
If machines over take monotonous and tedious tasks, humans should upgrade their
skills to remain their masters always.
What according to you is a better approach towards this ethical concern? Justify your
answer.
● AI taking over laborious jobs won’t create unemployment. It is just a groundless fear.
The standard view of technical change is that some jobs are displaced by the
substitution of machines for labour, but that the fear of total displacement is misplaced
because new jobs are created, largely due to the technology-fuelled increase in
productivity. Humans have always shifted away from work suitable for machines and to
other jobs.
● The basic fact is that technology eliminates jobs, not work. If this level of AI revolution
will happen, lots of job opportunities will be created. For example: 20-30 years ago,
being an accountant was a lucrative job, AI took over this job but this created a lot of
opportunities, it raised the demand of a software engineer, data scientist, etc.
● It will open doors to skillful jobs rather than doing laborious tasks.
● Thus, we will be able to cope with the level of major unemployment, if AI took over
laborious jobs.

CHAPTER 3: AI PROJECT CYCLE

One (01) Mark Questions

1. Name all the stages of an AI Project cycle.

Problem Scoping, Data Acquisition, Data Exploration, Modeling, Evaluation
2. What are sustainable development goals?
The Sustainable Development Goals (SDGs), also known as the Global Goals, were
adopted by all United Nations Member States in 2015 as a universal call to action to
end poverty, protect the planet and ensure that all people enjoy peace and prosperity.
OR
The Sustainable Development Goals (SDGs) or Global Goals are a collection of 17
interlinked goals designed to be a "blueprint to achieve a better and more sustainable
future for all" so that the future generations may live in peace and prosperity.
3. Name the 4Ws of problem canvases under the problem scoping stage of the AI
Project Cycle.
a. Who, b. what c. where d. why
4. What is the objective of evaluation stage?
It is to evaluate whether the ML algorithm is able to predict with high accuracy or not
before deployment.
 Two (02) Mark Questions
1. What are the two different approaches for AI modelling? Define them.
There are two approaches for AI Modelling; Rule Based and Learning Based.
The Rule based approach generates pre-defined outputs based on certain rules
programmed by humans. Whereas, machine learning approach has its own rules based
on the output and data used to train the models.
OR
Rule Based Approach Refers to the AI modelling where the relationship or patterns in
data are defined by the developer. The machine follows the rules or instructions
mentioned by the developer, and performs its task accordingly. Whereas in Learning
based approach, the relationship or patterns in data are not defined by the developer.
In this approach, random data is fed to the machine and it is left to the machine to
figure out patterns and trends out of it

2. What is a problem statement template and what is its significance?

The problem statement template gives a clear idea about the basic framework
required to achieve the goal. It is the 4Ws canvas which segregates; what is the
problem, where does it arise, who is affected, why is it a problem? It takes us straight
to the goal.

3. Explain any two SDGs in detail.

1. No Poverty: This is Goal 1 and strives to End poverty in all its forms everywhere
globally by 2030. The goal has a total of seven targets to be achieved.
2. Quality Education: This is Goal 4 which aspires to ensure inclusive and equitable
quality education and promote lifelong learning opportunities for all. It has 10 targets
to achieve.* (Any two goals can be defined)

4. Write the names for missing stages in the given AI project cycle:

Problem scoping, Evaluation

5. Draw the icons of the following SDGs:
Gender Clean Water and
Equality sanitation

6. What are the features of an Artificial Neural Network?

Any Artificial Neural Network, irrespective of the style and logic of implementation,
has a few basic features as given below.
 The Artificial Neural Network systems are modelled on the human brain and nervous
system.
  They are able to automatically extract features without feeding the input by
programmer.
 Every node of layer in a Neural Network is compulsorily a machine learning algorithm.
 It is very useful to implement when solving problems for very huge datasets.
OR
 It can work with incomplete knowledge and may produce output even with
incomplete information.
 It has fault tolerance which means that corruption of one or more cells of ANN does
not prevent it from generating output.
 It has the ability to learn events and make decisions by commenting on similar events.
 It has Parallel processing capability i.e. ANN have numerical strength that can perform
more than one job at the same time.
OR
 Neural Networks have the ability to learn by themselves and produce the output that
is not limited to the input provided to them.
 The input is stored in its own networks instead of a database; hence the loss of data
does not affect its working.
 These networks can learn from examples and apply them when a similar event arises,
making them able to work through real-time events.
 Even if a neuron is not responding or a piece of information is missing, the network
can detect the fault and still produce the output.
 They can perform multiple tasks in parallel without affecting the system performance

7. What is the purpose of getting AI Ready?

The world is changing with each day and we have huge data coming our way. The
purpose of getting AI ready means taking steps to collect data around relevant
systems, equipment, and procedures; and storing and curating that data in a way that
makes it easily accessible to others for use in future AI applications.
OR
The purpose of getting AI ready specifies the responsible and optimum use of huge
amount of data around us to create and implement into such systems and applications
which should make life of future generations more organized and sustainable. This
process may lead to better lives for mankind.

Four (04) Mark Questions

1. Explain the AI Project Cycle in detail.

The steps involved in AI project cycle are as given:
 The first step is Scope the Problem by which, you set the goal for your AI project by
stating the problem which you wish to solve with it. Under problem scoping, we look
at various parameters which affect the problem we wish to solve so that the picture
becomes clearer
 Next step is to acquire data which will become the base of your project as it will help
you in understanding what the parameters that are related to problem scoping.
 Next, you go for data acquisition by collecting data from various reliable and authentic
sources. Since the data you collect would be in large quantities, you can try to give it a
visual image of different types of representations like graphs, databases, flow charts,
maps, etc. This makes it easier for you to interpret the patterns in which your acquired
data follows.
 After exploring the patterns, you can decide upon the type of model you would build to
achieve the goal. For this, you can research online and select various models which
 give a suitable output.
 You can test the selected models and figure out which is the most efficient one.
 The most efficient model is now the base of your AI project and you can develop your
algorithm around it.
 Once the modelling is complete, you now need to test your model on some newly
fetched data. The results will help you in evaluating your model and hence improving
it.
Finally, after evaluation, the project cycle is now complete and what you get is your AI
project.

2. Draw the 4Ws problem canvas and explain each one of them briefly.
The 4Ws problem canvas is the basic template while scoping a problem and using this
canvas, the picture becomes clearer while we are working to solve it.

a) Who: The “Who” block helps you in analyzing the people getting affected directly or
indirectly due to it? Under this, you find out who the ‘stakeholders’ to this problem are
and what you know about them. Stakeholders are the people who face this problem
and would be benefitted with the solution.
b) What: Under the “What” block, you need to look into what you have on hand. At this
stage, you need to determine the nature of the problem. What is the problem and how
do you know that it is a problem?
c) Where: In this block, you need to focus on the context/situation/location of the
problem. It will help you look into the situation in which the problem arises, the
context of it, and the locations where it is prominent.
d) Why: in the “Why” canvas, think about the benefits which the stakeholders would get
from the solution and how would it benefit them as well as the society.

3. Differentiate between rule-based and learning-based AI modelling approaches.

Rule Based Approach: It refers to the AI modelling where the relationship or patterns
in data are defined by the developer. The machine follows the rules or instructions
mentioned by the developer, and performs its task accordingly.
For example, suppose you have a dataset comprising of 100 images of apples and 100
images of bananas. To train your machine, you feed this data into the machine and
label each image as either apple or banana. Now if you test the machine with the image
of an apple, it will compare the image with the trained data and according to the labels
of trained images, it will identify the test image as an apple. This is known as Rule
based approach. The rules given to the machine in this example are the labels given to
the machine for each image in the training dataset.
Learning Based Approach: In this approach, the machine learns by itself. It refers to
the AI modelling where the relationship or patterns in data are not defined by the
developer. In this approach, random data is fed to the machine and it is left on the
machine to figure out patterns and trends out of it. Generally, this approach is followed
when the data is un labelled and too random for a human to make sense out of it.

For example, suppose you have a dataset of 1000 images of random stray dogs of your
area. You would put this into a learning approach-based AI machine and the machine
would come up with various patterns it has observed in the features of these 1000
images which you might not have even thought of!
4. What is an Artificial Neural Network? Explain the layers in an artificial neural
network.
Artificial Neural Network: Modeled in accordance with the human brain, a Neural
Network was built to mimic the functionality of a human brain. The human brain is a
neural network made up of multiple neurons, similarly, an Artificial Neural Network
(ANN) is made up of multiple perceptrons.
A neural network consists of three important layers:
Input Layer: As the name suggests, this layer accepts all the inputs provided by the
programmer.
Hidden Layer: Between the input and the output layer is a set of layers known as
Hidden layers. In this layer, computations are performed which result in the output.
There can be any number of hidden layers
Output Layer: The inputs go through a series of transformations via the hidden layer
which finally results in the output that is delivered via this layer.

5. What is the need of an AI Project Cycle? Explain.

Project cycle is the process of planning, organizing, coordinating, and finally
developing a project effectively throughout its phases, from planning through
execution then completion and review to achieve pre-defined objectives.
Our mind makes up plans for every task which we have to accomplish which is why
things become clearer in our mind. Similarly, if we have to develop an AI project, the AI
Project Cycle provides us with an appropriate framework which can lead us towards
the goal.
The major role of AI Project Cycle is to distribute the development of AI project in
various stages so that the development becomes easier, clearly understandable and
the steps / stages should become more specific to efficiently get the best possible
output. It mainly has 5 ordered stages which distribute the entire development in
specific and clear steps: These are Problem Scoping, Data Acquisition, Data
Exploration, Modelling and Evaluation.

6. Explain the following:

a. Supervised Learning b. Unsupervised Learning

 Supervised learning is an approach to creating artificial intelligence (AI), where the
program is given labelled input data and the expected output results.
OR
 Supervised learning is a learning in which we teach or train the machine using data
which is well labelled that means some data is already tagged with the correct answer.
After that, the machine is provided with a new set of examples (data) so that
supervised learning algorithm analyses the training data (set of training examples)
and produces a correct outcome from labelled data.
OR
 In a supervised learning model, the dataset which is fed to the machine is labelled. It
means some data is already tagged with the correct answer. In other words, we can
say that the dataset is known to the person who is training the machine only then
he/she is able to label the data.
  Unsupervised Learning: An unsupervised learning model works on unlabeled
dataset. This means that the data which is fed to the machine is random and there is a
possibility that the person who is training the model does not have any information
regarding it. The unsupervised learning models are used to identify relationships,
patterns and trends out of the data which is fed into it. It helps the user in
understanding what the data is about and what are the major features identified by the
machine in it.
OR
 Unsupervised learning is the training of a machine using information that is neither
classified nor labelled and allowing the algorithm to act on that information without
guidance. Here the task of the machine is to group unsorted information according to
similarities, patterns and differences without any prior training of data.

7. Five sustainable Development Goals are mentioned below. Write 2 problems under
each goal that you think should be addressed for achieving the goal.
a. Quality Education
b. Reduced Inequalities
c. Life on Land
d. No Poverty
e. Clean Water and Sanitation

a. Quality Education:
i. Providing education remotely, leveraging hi-tech, low-tech and no-tech approaches;
ii. Ensure coordinated responses and avoid overlapping efforts;
iii. Ensuring return of students to school when they reopen to avoid an upsurge in
dropout rates.

b. Reduced inequalities:
i. Reduction of relative economic inequalities inequality in some countries having
poorest and most vulnerable communities.
ii. Improving the situations in countries with weaker health systems.

c. Life on Land:
i. Prevention of Deforestation caused by humans and restoration of land
ii. Preventions and cure of diseases that are transmissible between animals and humans

d. No Poverty
i. Creation of Strong social protection systems to prevent people from falling into
poverty
ii. Reduction of social exclusion, and high vulnerability of certain populations to disasters
and diseases.
iii. Responsible distribution of resources.
e. Clean Water and Sanitation
i. To increase access to clean drinking water and sanitation mostly in rural areas
ii. Managing our water sustainably to manage our production of food and energy.
 CHAPTER 7: NATURAL LANGUAGE PROCESSING

One (01) Mark Questions

1. What is a Chabot?
A chatbot is a computer program that's designed to simulate human conversation
through voice commands or text chats or both. Eg: Mitsuku Bot, Jabberwacky etc.
OR
A chatbot is a computer program that can learn over time how to best interact with
humans. It can answer questions and troubleshoot customer problems, evaluate and
qualify prospects, generate sales leads and increase sales on an ecommerce site.
OR
A chatbot is a computer program designed to simulate conversation with human users.
A chatbot is also known as an artificial conversational entity (ACE), chat robot, talk bot,
chatterbot or chatterbox.
OR
A chatbot is a software application used to conduct an on-line chat conversation via text
or text-to-speech, in lieu of providing direct contact with a live human agent.

2. What is the full form of NLP?

Natural Language Processing

3. While working with NLP what is the meaning of?

Syntax: Syntax refers to the grammatical structure of a sentence.
Semantics: It refers to the meaning of the sentence.

4. What is the difference between stemming and lemmatization?

Stemming is a technique used to extract the base form of the words by removing affixes
from them. It is just like cutting down the branches of a tree to its stems. For example,
the stem of the words eating, eats, eaten is eat.
Lemmatization is the grouping together of different forms of the same word. In search
queries, lemmatization allows end users to query any version of a base word and get
relevant results.
OR
Stemming is the process in which the affixes of words are removed and the words are
converted to their base form.
In lemmatization, the word we get after affix removal (also known as lemma) is a
meaningful one. Lemmatization makes sure that lemma is a word with meaning and
hence it takes a longer time to execute than stemming.
OR
Stemming algorithms work by cutting off the end or the beginning of the word, taking
into account a list of common prefixes and suffixes that can be found in an inflected
word.
Lemmatization on the other hand, takes into consideration the morphological analysis
of the words. To do so, it is necessary to have detailed dictionaries which the algorithm
can look through to link the form back to its lemma.
 Two (02) Mark Questions

1. What are the types of data used for Natural Language Processing applications?
Natural Language Processing takes in the data of Natural Languages in the form of
written words and spoken words which humans use in their daily lives and operates on
this.

2. Differentiate between a script-bot and a smart-bot. (Any 2 differences)

Script-bot Smart-bot
 A scripted chatbot doesn’t carry  Smart bots are built on NLP and
even a glimpse of A.I ML.
 Script bots are easy to make  Smart –bots are comparatively
difficult to make.
 Script bot functioning is very  Smart-bots are flexible and
limited as they are less powerful. powerful.
 Script bots work around a script ● Smart bots work on bigger
which is programmed in them databases and other resources
directly
 No or little language processing ● NLP and Machine learning skills
skills are required.
 Limited functionality ● Wide functionality

3. Define the following:

● Stemming
● Lemmatization

Stemming: Stemming is a rudimentary rule-based process of stripping the suffixes

(“ing”, “ly”, “es”, “s” etc) from a word.
Stemming is a process of reducing words to their word stem, base or root form (for
example, books — book, looked — look).

Lemmatization: Lemmatization, on the other hand, is an organized & step by step

procedure of obtaining the root form of the word, it makes use of vocabulary (dictionary
importance of words) and morphological analysis (word structure and grammar
relations).

The aim of lemmatization, like stemming, is to reduce inflectional forms to a common

base form. As opposed to stemming, lemmatization does not simply chop off inflections.
Instead it uses lexical knowledge bases to get the correct base forms of words.
OR
Stemming is a technique used to extract the base form of the words by removing affixes
from them. It is just like cutting down the branches of a tree to its stems. For example,
the stem of the words eating, eats, eaten is eat.
Lemmatization is the grouping together of different forms of the same word. In search
queries, lemmatization allows end users to query any version of a base word and get
relevant results.
OR
 Stemming is the process in which the affixes of words are removed and the words are
converted to their base form.
In lemmatization, the word we get after affix removal (also known as lemma) is a
meaningful one. Lemmatization makes sure that lemma is a word with meaning and
hence it takes a longer time to execute than stemming.
OR
Stemming algorithms work by cutting off the end or the beginning of the word, taking
into account a list of common prefixes and suffixes that can be found in an inflected
word.
Lemmatization on the other hand, takes into consideration the morphological analysis
of the words. To do so, it is necessary to have detailed dictionaries which the algorithm
can look through to link the form back to its lemma.

4. Mention some applications of Natural Language Processing.

Natural Language Processing Applications-
● Sentiment Analysis.
● Chatbots & Virtual Assistants.
● Text Classification.
● Text Extraction.
● Machine Translation
● Text Summarization
● Market Intelligence
● Auto-Correct

5. What is text normalization in NLP & why is it needed?

Since we all know that the language of computers is Numerical, the very first step that
comes to our mind is to convert our language to numbers.
This conversion takes a few steps to happen. The first step to it is Text Normalization.
Since human languages are complex, we need to first of all simplify them in order to
make sure that the understanding becomes possible. Text Normalization helps in
cleaning up the textual data in such a way that it comes down to a level where its
complexity is lower than the actual data.
6. Differentiate between Human Language and Computer Language.
Humans communicate through language which we process all the time. Our brain keeps
on processing the sounds that it hears around itself and tries to make sense out of them
all the time.
On the other hand, the computer understands the language of numbers. Everything that
is sent to the machine has to be converted to numbers. And while typing, if a single
mistake is made, the computer throws an error and does not process that part. The
communications made by the machines are very basic and simple.
Four 04 Mark Questions

1. Why are human languages complicated for a computer to understand? Explain.

The communications made by the machines are very basic and simple. Human
communication is complex. There are multiple characteristics of the human language
that might be easy for a human to understand but extremely difficult for a computer to
understand.
For machines it is difficult to understand our language. Let us take a look at some of
them here:
 Arrangement of the words and meaning - There are rules in human language. There are
nouns, verbs, adverbs, adjectives. A word can be a noun at one time and an adjective
some other time. This can create difficulty while processing by computers.
Analogy with programming language- Different syntax, same semantics: 2+3 = 3+2 Here
the way these statements are written is different, but their meanings are the same that
is 5. Different semantics, same syntax: 2/3 (Python 2.7) ≠ 2/3 (Python 3) Here the
statements written have the same syntax but their meanings are different. In Python 2.7,
this statement would result in 1 while in Python 3, it would give an output of 1.5.
Multiple Meanings of a word - In natural language, it is important to understand that a
word can have multiple meanings and the meanings fit into the statement according to
the context of it.
Perfect Syntax, no Meaning - Sometimes, a statement can have a perfectly correct syntax
but it does not mean anything. In Human language, a perfect balance of syntax and
semantics is important for better understanding.
These are some of the challenges we might have to face if we try to teach computers
how to understand and interact in human language.

2. What are the steps of text Normalization? Explain them in brief.

Text Normalizationin Text Normalization, we undergo several steps to normalize the

text to a lower level.

Sentence Segmentation - Under sentence segmentation, the whole corpus is divided into
sentences. Each sentence is taken as a different data so now the whole corpus gets
reduced to sentences.

Tokenisation- After segmenting the sentences, each sentence is then further divided into
tokens. Tokens is a term used for any word or number or special character occurring in
a sentence. Under tokenisation, every word, number and special character is considered
separately and each of them is now a separate token.
Removing Stop words, Special Characters and Numbers - In this step, the tokens which
are not necessary are removed from the token list.
Converting text to a common case -After the stop words removal, we convert the whole
text into a similar case, preferably lower case. This ensures that the case-sensitivity of
the machine does not consider same words as different just because of different cases.
Stemming In this step, the remaining words are reduced to their root words. In other
words, stemming is the process in which the affixes of words are removed and the
words are converted to their base form.
Lemmatization -in lemmatization, the word we get after affix removal (also known as
lemma) is a meaningful one.

With this we have normalized our text to tokens which are the simplest form of words
present in the corpus. Now it is time to convert the tokens into numbers. For this, we
would use the Bag of Words algorithm
 CHAPTER 8: EVALUATION
One (01) Mark Questions

1. Define Evaluation.
Moving towards deploying the model in the real world, we test it in as many ways
aspossible. The stage of testing the models is known as EVALUATION.
OR
Evaluation is a process of understanding the reliability of any AI model, based on outputs
by feeding the test dataset into the model and comparing it with actual answers.
OR
Evaluation is a process that critically examines a program. It involves collecting and
analyzing information about a program’s activities, characteristics, and outcomes. Its
purpose is to make judgments about a program, to improve its effectiveness, and/or to
inform programming decisions.
2. Which two parameters are considered for Evaluation of a model?

Prediction and Reality are the two parameters considered for Evaluation of a model.
The “Prediction” is the output which is given by the machine and the “Reality”is the real
scenario, when the prediction has been made?

Two (02) Mark Questions

1. What is meant by Overfitting of Data?

Overfitting is "the production of an analysis that corresponds too closely or exactly to a
particular set of data, and may therefore fail to fit additional data or predict future
observations reliably".
(OR)
An Overfitted Model is a statistical model that contains more parameters than can be
justified by the data. Here, to evaluate the AI model it is not necessary to use the data that
is used to build the model. Because AI Model remembers the whole training data set,
therefore it always predicts the correct label for any point in the training dataset. This is
known as Overfitting
(OR)
Models that use the training dataset during testing, will always results in correct output. This is
known as overfitting.

2. What is Accuracy? Mention its formula.

Accuracy is defined as the percentage of correct predictions out of all theobservations.
A prediction is said to be correct if it matches reality. Here we have twoconditions in which
the Prediction matches with the Reality, i.e., True Positive and True Negative. Therefore,
Formula for Accuracy is

Where TP = True Positives, TN = True Negatives, FP = False Positives, and FN = False

Negatives.
3. What is Precision? Mention its formula.

Precision is defined as the percentage of true positive cases versus all the cases where the
prediction is true.

That is, it takes into account the True Positives and False Positives.

4. What are the possible reasons for an AI model not being efficient? Explain.
Reasons of an AI model not being efficient:

a. Lack of Training Data: If the data is not sufficient for developing an AI Model, or if the
data is missed while training the model, it will not be efficient.

b. Unauthenticated Data / Wrong Data: If the data is not authenticated and correct, then
the model will not give good results.
c. Inefficient coding / Wrong Algorithms: If the written algorithms are not correct
and relevant, Model will not give desired output. Not Tested: If the model is not
tested properly, then it will not be efficient.
d. Not Easy: If it is not easy to be implemented in production or scalable.
e. Less Accuracy: A model is not efficient if it gives less accuracy scores in production
or test data or if it is not able to generalize well on unseen data.
(Any three of the above can be selected)

Four (04) Mark Questions

1. What is a confusion matrix? Explain in detail with the help of an example.

Confusion Matrix:
A Confusion Matrix is a table that is often used to describe the performance of a
classification model (or "classifier") on a set of test data for which the true values are
known.
(or)

A 2x2 matrix denoting the right and wrong predictions might help us analyse the rate of
success. This matrix is termed the Confusion Matrix. The following confusion matrix table
illustrates how the 4-classification metrics are calculated (TP, FP, FN, TN), and how our
predicted value compared to the actual value in a confusion matrix
Let’s decipher the matrix:

The target variable has two values: Positive or Negative

The columns represent the actual values of the target variable

The rows represent the predicted values of the target variable
True Positive, True Negative, False Positive and False Negative in a Confusion Matrix

True Positive (TP):

The predicted value matches the actual value
The actual value was positive and the model predicted a positive value

True Negative (TN)

The predicted value matches the actual value
The actual value was negative and the model predicted a negative value

False Positive (FP) – Type 1 error

The predicted value was falsely predicted
The actual value was negative but the model predicted a positive value also known as the
Type 1 error

False Negative (FN) – Type 2 error

The predicted value was falsely predicted
The actual value was positive but the model predicted a negative value also known as the
Type 2 error

Example:
Case: Loan (Good loan & Bad loan)

The result of TP will be that bad loans are correctly predicted as bad loans.

The result of TN will be that good loans are correctly predicted as good loans.

The result of FP will be that (actual) good loans are incorrectly predicted as bad loans.

The result of FN will be that (actual) bad loans are incorrectly predicted as good loans.
The banks would lose a bunch of money if the actual bad loans are predicted as good loans
due to loans not being repaid. On the other hand, banks won't be able to make more
revenue if the actual good loans are predicted as bad loans. Therefore, the cost of False
Negatives is much higher than the cost of False Positives.