CHAPTER 1

INTRODUCTION TO AI
Task (Page 146)
1. Accept all relevant answers.
2. By 2030, AI will replace most number of jobs that are done by Human like for example most of the cleaning jobs will be
done by Robots. There will be Bots, AI enabled that will be dealing with people with stress – CBT.
3. Computers can do tasks that are repetitive like large statistical calculations, better than humans.

Reboot (Page 149)

a. Yes d. Yes

b. No e. Yes

c. No

Reboot (Page 158)

1. Google Image Search – Computer Vision
2. Akinator – Data
3. Face-Recognition System in Mobile – Computer Vision
4. Cortana – Natural Language Processing

Task (Page 159)

Mobile phones, smart watches, Alexa, smart TV, smart lights and all gadgets that are centrally connected in a smart house.
For example, your phone calendar, disables the security systems as soon as you enter the house. It enables the security
system when you proceed for vacations. All electronic gadgets switch on their power saving mode.

Task (Page 162)

1. Device Name: AI Energy Mode, a power feature from Samsung's Smart Things Energy.
It is powered to bring the office in a power saving mode whenever it is not in use. Impressive savings in energy and cost
have been recorded across the board.
2. Attendance: Face scanner to mark the attendance
Name of Device/Software – Lystface.
Its a facial recognition attendance management solution that works in real time. It's an android based facial attendance
system.

Task (Page 163)

1. Attendance System: The RFID system card should be installed to track the students. The advantage is that the efforts of the
teachers can be reduced and the student can be tracked.
2. Jukebox-Music in Bathrooms: washroom jobs can be noise free if the music is playing.
3. Entries to labs with IRIS – entry system – No unauthorised student can use the facilities if the timetable is not allocated.
4. Autonomous Timetable system: No delay in arrangement for the absent teachers can be covered effectively.
Reboot (Page 167)
1. Climate Action 6. Responsible Consumption and Production
2. Partnership for the Goals 7. Life on Land
3. No Poverty 8. Clean Water and Sanitation
4. Quality Education 9. Decent Work and Economic Growth
5. Sustainable Cities and Communities

Reboot (Page 182)

1. Niramai Health Analytix 2. Haptik.ai 3. Kissan AI

Task (Page 186)

1. Parking Entry 4. Security checks
2. Registration in Hospitals 5. Restaurants: To take Orders
3. Banks: Withdrawal and Deposit

Exercise
Unsolved Questions
SECTION A (Objective Type Questions)

A. Multiple Choice Question

1. A 6. B 11. B
2. D 7. D 12. A
3. D 8. A 13. A
4. C 9. B
5. D 10. C

B. Fill in the blanks

1. Precision 5. Surveillance 9. Data Science
2. Affordable, skilled engineers 6. Justice 10. HDFC
3. Hanson Robotics 7. Coding 11. Big Data
4. Analysis, Prediction 8. Healthcare, Construction 12. Data

C. True & False

1. True 5. True 9. True
2. False 6. True 10. False
3. True 7. False 11. False
4. True 8. False 12. True
 SECTION B (Subjective Type Questions)
A. Short Answer Type Question
1. Some applications of CV in AI are facial lock in smartphones, unusual behaviour detection, object classification, etc.
2. Areas where AI has made a remarkable impact are:
a. Security surveillance b. Education c. Space exploration
3. The main focus of AI would be to replace humans in hazardous jobs. Fields like medicine, industry, environment, defense,
wherever humans are vulnerable, it will be replaced with machines with human-like intelligence.
4. Data is a domain of AI that is related to input to the AI machine. AI requires large amounts of data to find the latest trends and
patterns. More the data, the better will be the analysis and more accurate would be the prediction.
5. The main goal of smart cities is to optimise the economic growth of the city and improve quality of life for people with the use
of technology and data analysis.
6. Smart Homes are homes that use internet connected devices to empower remote monitoring and management of appliances and
devices such as for lighting and heating.
7. The goal of this SDG is to end hunger, achieve food security, improve nutrition, and promote sustainable agriculture. It also
aims to seek sustainable solutions to end hunger in all its forms by 2030 and to achieve food security.
8. A Sustainable Smart City is a city that use technology to provide services and better citizen welfare. It uses Information and
Communication Technology (ICT) to communicate, deliver welfare schemes, improve operational efficiency, and better quality
of government services. The main goal of smart cities is to optimise the economic growth of the city and improve the quality of
life for people with the use of technology and data analysis
9. LaMDA is the latest breakthrough in natural language understanding. It is a language model for dialogue applications and its
open domain, which means its design to converse on any open-end topic.
10. Astronomers used AI to sift through years of data obtained by the Kepler telescope to
identify a distant eight-planet solar system. AI is also being used for NASA's next mission to Mars, the AEGIS— a Mars based
AI robot, already on the planet is responsible to handle autonomous targeting of cameras in order to perform investigations in
Mars.
11. With rapid development of AI, the fear of unemployment is constant. Jobs in manufacturing, agriculture, food service, retail,
transportation and logistics, and hospitality are some of the industries likely to be affected. The majority of the repetitive
12. One of the benefits of AI for business is that it handles repetitive tasks across an organization so that employees can focus on
creative solutions, complex problem solving, and impactful work.
13. Artificial Intelligence (AI) is a branch of computer science that simulates human intelligence into machines, especially in
computer systems, so that they can think and perform actions similar to humans.

B. Long Answer Type Question

1. General AI: It is also termed as Strong AI. Machines with the following characteristics will fall in this category. Machines that
would perform a wider range of different tasks with the intelligence like that of humans. It is a step ahead of Weak AI by
including problem-solving, learning and development.
• Strong AI: At present, we have not developed any such machines.
• Worldwide research is now focused on developing machines with strong AI. As these systems are in their research stage, it may
take a lot of time and effort to develop these.
• An example of Strong AI could be a machine hearing "good morning" and deciding to turn on the coffee maker.
Artificial Super AI-
• Super AIs are in their hypothetical stage. Super AI systems would surpass the human intelligence in performing any task will
fall in the category of Super AI.
• Super AI will be able to understand humans and will be able to evoke their own emotions and desires as well. It can be
considered as the next stage of Strong AI and developing such machines will be a challenging task.
2. Answer
a. Big Data Engineer: The role of a Big Data Engineer is to create an ecosystem for the business systems to interact efficiently.
Their primary task is to build and effectively administer big data of an organization. They also have to carry out the function of
obtaining outcomes from big data in a robust manner.
b. Machine Learning Engineer: Machine learning engineers are involved in building and maintaining self-running software that
facilitates machine learning initiatives. They are in continuous demand by the companies and their position rarely remains
vacant. They work with huge chunks of data and possess extraordinary data management traits.
c. Robotics Scientist: A reduction in jobs will indeed take place due to the emergence of robotics in the field of AI. Conversely,
jobs will also rise as robotics scientists are in incessant demands by major industries for programming their machines.
3. The following are some of the advantages of smart homes:
i. It's convenient to manage all the devices from a single application.
ii. Smart devices can maximise house security. Home automation systems can be connected to surveillance cameras,
automated door locks, motion detectors for increased security.
iii. With smart devices there's a flexibility of adding new devices with ease.
iv. The applications give an insight to your home activities. You can keep a watch on the number of hours you watch
television, the hottest hour of the day, energy consumption, control of heating and cooling, etc.
v. Remote control of household appliances can be a convenience on a busy day. You can switch on the air conditioner before
reaching home, check if the lights are switched off, control the temperature of your oven, etc.
4. We use our vision to sense and identify objects around us. In the same way, AI machines use Computer Vision domain to
understand their surroundings. Computer Vision (CV) is the domain of Artificial Intelligence that is used to train computers to
read, process and analyse visual data in the same way as humans do. The type of data in CV is images and videos. The AI
machine collects data from digital images and videos, and then process the data to identify the objects in the image/video. For
example, a self-driven car scans the live objects like traffic signal, analyse the scanned image and then creates the 3D version of
it. After that, the car decides whether to run or stop. Some other applications of CV in AI are facial lock in smartphones,
unusual behaviour detection, object classification, home security systems, office security systems and drone-based surveillance
systems.
5. Smart Cities are cities that uses technology to provide services and better citizen welfare.
a. It uses Information and Communication Technology (ICT) to communicate, deliver welfare schemes, improve operational
efficiency, and better quality of government services.
b. The main goal of smart cities is to optimize the economic growth of the city and improve the quality of life for people
with the use of technology and data analysis.
c. Lights that adapt to daylight make smart street lights. Parking sensors to intimate about available parking lots, automated
garbage collection are a few examples of a smart city. *The main characteristic of smart cities is to create an inclusive and
sustainable environment that is centered around people’s wellbeing.
6. A smart school is a technology-based teaching-learning environment for both teachers and students. ICT is used to achieve
smart schools' educational objectives, prepare child friendly curriculum, assessment, and teaching-learning mechanism.
Children are prepared to be part of the Information Age:
a. Use of digital devices like laptops, tablets instead of conventional books. No longer students have to carry big bags for
those books. All the subjects can be learned, stored, sorted on a single device.
b. Easy access to information on the internet is available not only to students but it is a benefit for the teachers as well. They
can learn beyond the books using smart boards.
* A teaching environment becomes very interactive with the use of technology. Means of communication is better, one can
 connect to peers outside the classroom online. Even the teacher-student bond has improved with technology as the time gap of
request and response is reduced.
7. Goal 14: Life Below Water
Conserve and sustainably use the oceans, seas and marine resources for sustainable development. It aims to reduce water
pollution, protect and restore ecosystems, sustainable fishing, conserve coastal and marine areas, reduce ocean acidification,
end subsidies aiming to reduce overfishing and increase the economic benefits from sustainable use of marine resources.
Goal 15: Life On Land
Protect, restore, and promote sustainable use of terrestrial ecosystems, sustainably manage forests, and combat desertification.
It aims to conserve ecosystems, end deforestation, protect biodiversity and natural habitats, eliminating poaching and
trafficking of endangered species.
8. The development of autonomous vehicles will revolutionaries the transportation system. Waymo, after many test drives,
launched their first public riding services. Waymo's AI software crunches data from vehicles lidar, camera, GPS, and cloud
services to produce control signals that operate the driver-less vehicle.
9. a. Healthcare for Assisting Doctors: For saving human lives the medical industry is relying on AI on many fronts. Healthcare
organisations are using IBM Watson for medical diagnosis. Google's DeepMind has successfully developed a system that can
analyse retinal scans and spot symptoms of sight-threatening eye diseases.
b. AI in Education for Automated Grading System: AI in the assessment process provides real-time learning feedback to
teachers and students. Through Machine Learning and data analysis using AI, human patterns of data are studied. This helps in
a quick and fair grading system without human interventions.
c. AI in Agriculture: The world will need to produce 50 percent more food by 2050 as we are exhausting our resources. The
only way this can be possible is when we are using it more wisely. AI can help farmers to get more from the land, and use
resources more sustainably.
10. Email Spam Filters: Email categorization and spam filters are one of the powering features of AI that affect our inbox. Simple
rule-based filters are used to mark spam or put email into various categories as Primary, Social, Promotion or Important.
11. a. Manufacturing and pharmaceutical work b. Doctors c. Soldiers
12. Some of the sources of AI Bias are:
a. Data: AI systems are the result of the data that is fed into them. The data used to train the AI system is the first step to check
for biasness. The dataset for AI systems should be realistic and need to be of a sufficient size. However, the largest data
collected from the real world may also reflect human subjectivity and underlying social biases. The Amazon AI recruitment
system is a good example. It was found that their recruitment system was not selecting candidates in a gender-neutral way. The
machine learning algorithm was based on the number of resumes submitted over a period of 10 years, that most of them were
men, so it favored men over women.
b. Algorithms: The algorithms in itself do not add biasness to an AI model, but it amplifies the biasness. Let's see an example of
an image classifier model. Its trained on images in the public domain— pictures of people's kitchens. It so happens that most of
the images are of women rather than men. AI algorithms are designed to maximise the accuracy. Therefore, an AI algorithm
may decide that the people in the kitchen are women despite the fact some of the images are of men.
c. Developers: The last source of AI bias is developers. Those who design AI models focus on achieving the desired goals. On
that path at times, the biases of the developers are reflected in their models. It's important to note here that the ethics and AI
bias are not the problems of the machine but the humans behind the machines.

Competency-based/Application-based questions:
1. Metadata collected from the user’s history and interactions.
2. Vikram can install an application that provides augmented reality (AR) features and various filters to enhance and customize
images are:
 a. PhotoDirector d. PicsArt
b. YouCam Perfect e. Snapseed
c. Pixlr f. Adobe Photoshop Camera
3. Answer
a. Disadvantages of AI are:
The disadvantages are things like costly implementation, potential human job loss, and lack of emotion and creativity.
b. AI is now perfect in performing routine jobs so such non-creative jobs will inevitably vanish soon. AI has the potential to
increase productivity, create new jobs, and raise living standards. However, by its very nature of performing “non-routine”
tasks formerly thought to be strictly the domain of humans, AI is likely to disrupt large swaths of jobs and tasks.
c. These could include data detectives or scientists, prompt engineers, robotics engineers, machine managers, and programmers,
particularly those who can code in Python which is key for AI development.
d. Although lives of people do not improve if they keep on being unskilled. Unskilled people will have difficulties in growth and
personal development.
e. 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 manpower
keeping in mind the growing world population
4. d
5. a

Deep Thinking (Page 200)

1. AI as evil:
a. Too much Personal information captured and stored by the apps.
b. Data leakage.
c. No-Ethics of the machines
d. Biasness of the technology
3. People changing their career one AI takes over:
i. Planners: Now building/offices can be designed using software.
ii. Reduced Bank employees.
iii. HR managers
iv. Telemarketing
v. Book keeping clerks
vi. Computer Support specialists
vii. Advertising Sales people
viii. Receptionists
ix. Proofreaders
x. Market Research Analysts
 CHAPTER 2
AI PROJECT CYCLE

Reboot (Page 212)

1. Problem Scoping 2. Data Acquisition 3. Data Exploration 4. Modelling 5. Evaluation

Task (Page 212)

1. List of people who have access to the flight, that is passenger maintenance and engineering staff associated with the flight, crew
members of flight, flight officials having access to the flight.

2. Criminals who have explicitly shown interest in his escape on any media.

3. Background of the criminal, and who have been his associates in crime and have still not been captured.

4. Background of the security team accompanying the criminal.

5. Flight stop-overs, and who all can have access to the flight at the time of stop-over and the duration of the flight. List of
components of your system to detect unauthorised access are as follows:

a. face scanner like BioNIC F7

b. Database management system like to store images like MongoDB

c. Facial security cameras for entry places other than main door of the Aircraft
We test algorithms to find out which algorithm, out of our shortlisted ones, produces most accurate results, when different
combination of people are sent in front of the camera in the aircraft for testing.

Task (Page 220)

Data features needed
1. Names of the participating restaurants
2. Categories of food for study
3. Amount of average food wasted on daily basis under each category.
4. Average losses due to each food category.
• Features collected will let us know where to act in order to solve the problem.
• We can collect the data from the restaurants
• Data can be collected on weekly basis
• Without enough data we won’t be able to make out correct analysis and won’t be able to find out solutions for reducing food
wastage.
• It is required that a restaurant should know what material it should buy in lesser quantity to reduce wastage.
• By deploying solutions for few weeks and monitoring improvement.
• Analysis provides aground for the solutions to be taken.

Reboot (Page 222)

1. Surveys 2. Web scraping 3. Sensors
4. Cameras 5. Observations
 Exercise
Unsolved Questions
Section A(Objective Type Question)
A. Multiple Choice Question
1. B 7. C 13. C
2. C 8. B 14. D
3. A 9. D 15. B
4. D 10. A 16. D
5. A 11. D 17. A
6. A 12. B
B. Fill in the blanks

1. AI project Cycle 6. Elements, interconnections 11. Pie

2. Evaluation 7. Cameras 12. Decision tree

3. Data Exploration 8. System maps 13. Rule-based

4. Solution 9. Data visualization 14. Accuracy

5. Testing data 10. Unstructured data 15. Pixel

C. True False

1. False 6. True 11. True

2. True 7. False 12. False
3. False 8. True 13. True
4. False 9. False 14. True
5. True 10. False 15. False

SECTION B (Subjective Type Questions)

A. Short Answer Type Question
1. AI project cycle is the process of converting the real-life problem into an AI-based model. The project cycle framework is
designed to help project managers guide their projects successfully from start to end. The purpose of the project life cycle is
to create an easy-to- follow framework to guide projects and leads us towards our goals.

2. Modelling or data modelling is defined as the process of designing decision-making algorithms that has to be trained on a set
of data (which was acquired at the data acquisition stage for the problem you scoped in the problem scoping stage) and apply
that learning to recognize certain types of patterns.

3. AI Project Cycle has 5 stages:

i. Problem Scoping

ii. Data Acquisition

iii. Data Exploration

iv. Modelling

v. Evaluation
4. There are two types of data:
Training Data: It is data on which we train our AI project model. It is basically to fit the parameters of the project for the
model. In training data, the output is available to the model.
Testing Data: It is used to check the performance of an AI model. In testing data, the data is not seen for which the
predictions have to be made.
5. Data can be collected from various sensors like collecting environmental data and stored in some data storage solutions.
Sensors are connected through gateways which enable them to collect live data in the offline mode.
6. There are times using the internet, we acquire unauthentic data from websites for our AI project. Extracting private data can
be an offence.
So, keeping this in mind we should ensure the data is collected from open-sourced websites hosted by the government. They
are one of the most reliable and authentic sources of information.
7. (This question was printed incorrectly in the book, please correct it in your textbook.)
Question: What is root node in a decision tree?
A root node is the first node of a decision tree and it represents the entire set of data.
8. Data is the base for any AI project to be built. When the data is acquired, it's important to check if it's from a reliable and
authentic source for the accuracy of the project.
9. It is a data visualization tool provided by Microsoft. It is freely available to download and use.
10. It is a combination of a bubble chart, data visualization and a map. It is used to visualize location and proportion using
circles over geographical regions with the area of the circle being proportional to its value in the dataset.
11. (This question was printed incorrectly in the book, please correct it in your textbook.)
Questions: What is child node?
A sub-node in a decision tree that falls under another node.

12. Pixel It is an example of a machine learning approach which is used in computer vision applications. The graphics or
images created in computers are pixel-based images. It shows how the computer classifies the images and reads them.

13. Learning based approach refers to the model where the relationship or patterns in the data are not defined by the developer.
Random data is fed into the machine and the machine develops its own pattern or trends based on data outputs.

14. (This question was printed incorrectly in the book, please correct it in your textbook.)
Questions: What is web scrapping?
Ans. Web scraping or Data scraping is the method of downloading information from the World Wide Web (WWW) and
storing it onto your computer for later reference.
15. Machine learning aims at making a machine that can learn through data and solve complex problems. Deep learning aims at
building neural network that can help in discovering patterns or trends.

B. Long Answer Type Question

1. AI project cycle is the process of converting the real-life problem into an AI based model. The project cycle framework is
designed to help project managers guide their projects successfully from start to end. The purpose of the project life cycle
is to create an easy-to- follow framework to guide projects. The AI project cycle provides us with an appropriate
framework which can lead us towards our goal.

• Problem Scoping: The first stage of an AI project cycle is problem scoping to identify the problem and have a vision
to solve it. Problem scoping means selecting a problem and finding a solution for it using AI technology. The project
identifies the area in which AI can be used to provide a solution.

Many times we are unable to observe any problem in our surroundings. In that case, we can take a look at the
Sustainable Development Goals. 17 goals have been announced by the United Nations which are termed as
the Sustainable Development Goals. The aim is to achieve these goals by the end of 2030.
 • Modelling: It is the design phase of the project cycle. In this, we select the best way to reach the solution. It requires
the process of selecting the right algorithm to develop a working model for the project. In this step, the algorithm is
converted into a model.

• Data Acquisition: The term data acquisition means collecting raw data for the purpose of reference or analysis for the
project. The data can be in the form of text, numbers, images, videos or audio. The data acquisition system allows us to
obtain valuable information about reality to improve the performance of the project.
2. Answer

Our MIIT officials Who?

Have a problem of Conduct an examination What?
While No unfair means should be used in the examination or no unauthorized Where?
person should enter the examination center.
An ideal solution would A system which can check who all are entering the center, and the system Why?
should raise an alert if it finds any unauthorized person entering so that
they have fair admission selection.

3. Answer

Our IT Company Who?

Have a problem of Categorized support tickets What?
While In operations where they are not able to classify support tickets properly Where?
which leads to delay in response.
An ideal solution would A classification system which can categories the support tickets correctly Why?
and in less time.

4. A system map is a diagrammatic representation of a set of things working together. It focuses on the components and
boundaries of a system. System map helps us to find relationships between different elements of the problem which we have
scoped. It helps to find a solution to achieve the goal of our project. We use system maps to understand the complex issues
that have inter connected factors affecting each other.
5. We use system maps to understand the complex issues that have inter connected factors affecting each other. A system
comprises of:
• Elements: These are different, discrete elements within the system.
• Interconnections: These are the relationships that connect the elements.
Rules for system maps are:
a. The circles represent elements.
b. Arrows are used to represent relationships/interconnections.
c. The '+' and '-' signs are indicators of the nature of a relationship. The arrowhead depicts the direction of the effect and
the sign (+ or -) shows their relationship.
d. If the arrow goes from X to Y with a + sign, it means that both are directly related to each other. That means if X
increases, Y also increases and vice versa.
e. If the arrow goes from X to Y with a -sign, it means that both the elements are inversely related to each other. That
means if X increases, Y would decrease and vice versa.

6. There are various sources to collect relevant data for our project:

• Surveys: Data can be collected from online surveys, telephonic surveys or in person surveys and collect responses.
Surveys are a way of collecting data from a group of people in order to gain information and insights into various topics
 of interest. The process involves asking people for information through questionnaires which can be online or offline. It
can be considered as a data source.

• Web Scraping: Data or information can also be extracted from a website. Web scraping or Data scraping is the method of
downloading information from the World Wide Web (WWW) and storing it onto your computer for later reference. The
data collected in this way is an online data.

• Sensors: Data can also be collected from various sensors like collecting environmental data and stored in some data
storage solutions. Sensors are connected through gateways which enable them to collect live data in the offline mode.

• Cameras: Data can be seen, written down or recorded onto the computer. Cameras are used to collect data in the form of
images. CCTV, web cameras, surveillance cameras are big sources of visual data that can be acquired from various
places.

• Observations: It is a method of collecting data by watching facts as they occur. Using the observation technique data can
be analysed and used for testing the model.

• Application Programming Interface (APIs): APIs are a set of functions and procedures that allow one application to
connect to another. So, one of the ways of collecting data is through APIs that can be used to collect data from social
media services for analysis.

7. Data exploration refers to the techniques and tools used to visualize data through complex statistical methods.

• It is the process of analyzing a large data set.

• Data exploration means to find the patterns and trends in the data. It is the third stage in the AI project cycle and the
initial step in data analysis. It is used to understand what is in a dataset and the characteristics of the data.

• Data exploration cleans the big data to provide an input to an AI project. Terabytes of data sitting in the data centre
unused is a burden, if correctly processed it can become digital gold.
8. Here are 10 elements of good data visualization that can help you present information that readers can process quickly and
easily
• Clear Headings and Keys • Relevant Comparisons. • Add design elements.
• Obvious Trends. • Lots of Data/Evidence. • Consolidated Information.
• Simple Analysis. • Summaries of Key Points.

9. Difference-

Artificial Intelligence Machine Learning

AI aims at making a machine that mimics human Aims at making a machine that can learn through data and solve
intelligence. complex problems

It is a subset of data science. It is a subset of AI.

It is the simulation of intelligence in machines. It is the training of machines to take decisions with experience.

10. Following are some of the important points to consider while designing a decision tree:
• There can be a possibility of multiple decision trees which lead to correct prediction for a single dataset. The simplest one
should be chosen.
• The dataset might contain redundant data at times, which does not have any reference while creating a decision tree.
Therefore, it is necessary that only those parameters that affect the output directly should be included.
• While making Decision Trees, one should take a look at the dataset given to them and try to figure out what pattern does
the output leaf follow. Try selecting any one output and on its basis, find out the common links which all the similar
outputs have.
11. Decision trees are tools that follow a rule based approach that uses a tree-like model of decisions and their possible
 consequences. It is a kind of flow chart, where the flow starts at the root node and ends with a decision made at the leaves. It
is used to depict conditions and their outcomes. It is one of the most widely used and practical methods for supervised
learning.
The decision tree starts from the root node just like the structure of a tree with two different ways or conditions: Yes or No.
The forks or diversions are known as Branches of the tree. The branches either lead to another decision/ question node or
they lead to another condition for decision, which is known as leaf node. If you look closely at the image, it looks like an
inverted tree with roots above and leaves below
12. Machine Learning: Machines need to learn the ways of humans by learning the techniques and processes. So machine
learning is a subset of artificial intelligence that uses statistical methods that enable machines to improve with experiences.
So machines learn from their mistakes and take them into consideration in the next iteration, this way they keep improving
with experience. For example, Snapchat filters and Netflix recommendations.