Mahavir Polytechnic CO6I-ETI-UNIT 1

Mahavir Polytechnic, Nashik

Department of Computer Engineering
Year: TY Subject: ETI (22618)

UNIT 1: Artificial Intelligence Marks: 12

Course Outcome 1: Describe machine learning and data concepts.

Syllabus:
1.1 Introduction of AI
• Concept, Scope of AL, Components of AI
1.2 Data Visualization
• Data types in data visualization, Scales map of data values in aesthetics
Use of colors to represent data values
• Representing - Amounts, Distribution, and Proportions
1.3 Data Storytelling
• Introduction, Ineffectiveness of Graphical representation of data
Explanatory Analysis Who, What, How
1.4 Concept of machine learning & deep learning

1.1 Introduction of AI
A branch of Computer Science named Artificial Intelligence (AI) pursues creating the computers
/ machines as intelligent as human beings. John McCarthy the father of Artificial Intelligence described
AI as, “The science and engineering of making intelligent machines, especially intelligent computer
programs”. Artificial Intelligence (AI) is a branch of Science which deals with helping machines find
solutions to complex problems in a more human-like fashion.

What Does Artificial Intelligence (AI) Mean?

Artificial intelligence (AI), also known as machine intelligence, is a branch of computer science that
focuses on building and managing technology that can learn to autonomously make decisions and carry
out actions on behalf of a human being.

Dept. Of Computer Engineering Page 1

Mahavir Polytechnic CO6I-ETI-UNIT 1

ए .ए , :

.ए ,
.

AI is not a single technology. It is an umbrella term that includes any type of software or hardware
component that supports machine learning, computer vision, natural language understanding (NLU) and
natural language processing (NLP).

Today’s AI uses conventional CMOS hardware and the same basic algorithmic functions that drive
traditional software. Future generations of AI are expected to inspire new types of brain-inspired circuits
and architectures that can make data-driven decisions faster and more accurately than a human being
can.

ए .ए
.

.
.

(John McCarthy) 1956 .

. .

ए .

ए .
ए ए . .

ए ए
.

Data : Data is defined as symbols that represent properties of objects events and their environment.
Information: Information is a message that contains relevant meaning, implication, or input for
decision and/or action.

Dept. Of Computer Engineering Page 2

 Mahavir Polytechnic CO6I-ETI-UNIT 1

Knowledge: It is the (1) cognition or recognition (know-what), (2) capacity to act(know-how),

and(3)understanding (know-why)that resides or is contained within the mind or in the brain.
Intelligence: It requires ability to sense the environment, to make decisions, and to control action.

What is Data in– ?

, ए

. ,
.ए . Raw data

( ) ए
.

: ए
, . .

. :

 ( )
 ( )

 ( )


, ( ) ए
. CPU , ( ) ( )

Dept. Of Computer Engineering Page 3

Mahavir Polytechnic CO6I-ETI-UNIT 1

, , , , :1 0
. Bit ए ए . Byte

. .

Concept:
Artificial Intelligence is one of the emerging technologies that try to simulate human reasoning in AI
systems The art and science of bringing learning, adaptation and self-organization to the machine is the
art of Artificial Intelligence. Artificial Intelligence is the ability of a computer program to learn and
think. Artificial intelligence (AI) is an area of Computer science that emphasizes the creation of
intelligent machines that work and reacts
like humans. AI is built on these three important concepts

Machine learning: When you command your smartphone to call someone, or when you chat with a
customer service chatbot, you are interacting with software that runs on AI. But this type of software
actually is limited to what it has been programmed to do. However, we expect to soon have systems that
can learn new tasks without humans having to guide them. The idea is to give them a large amount of
examples for any given chore, and they should be able to process each one and learn how to do it by the
end of the activity.

“ ”( ) ?

? ? ( !!)

.
. , ,

, .

Dept. Of Computer Engineering Page 4

Mahavir Polytechnic CO6I-ETI-UNIT 1

. ( , ,

computer program) “ ”( , machine learning, ML)

.

, , ( , data)

(train) . (patterns) .ए
ए .

“ ”( ) , -
,

. ,
.

ए (data) ए

, .

ए .

ए .

,
. ?

ए ?
.

ए .

Dept. Of Computer Engineering Page 5

Mahavir Polytechnic CO6I-ETI-UNIT 1

Machine Learning Method ?

.
.

ए ए

. ( )
. .

ए
, .

Deep learning: The machine learning example I provided above is limited by the fact that humans still
need to direct the AI’s development. In deep learning, the goal is for the software to use what it has
learned in one area to solve problems in other areas. For example, a program that has learned how to
distinguish images in a photograph might be able to use this learning to seek out patterns in complex
graphs.
डीप लर्निंग हे एक मशीन लर्निंग तंत्र आहे जे कॉम्प्युटरला ते करायला र्शकवते जे नैसर्गिकररत्या मानवां ना
येते: उदाहरणाद्वारे र्शका. डरायव्हरलेस गाड्ां मागील सखोल र्शक्षण हे एक महत्त्वाचे तंत्रज्ञान आहे , ज्यामुळे त्यां ना

थां बण्याचे र्चन्ह ओळखता येते र्कंवा पादचाऱ्याला र्दव्याच्या चौकटीपासून वेगळे करता येते. फोन, टॅ ब्लेट, टीव्ही
आर्ण हँ ड्स-फ्री स्पीकर यां सारख्या ग्राहक उपकरणां मध्ये व्हॉइस कंटर ोलची गुरुर्कल्ली आहे . सखोल र्शक्षणाकडे
अलीकडे आर्ण चां गल्या कारणास्तव खूप लक्ष र्दले जात आहे . हे असे पररणाम साध्य करत आहे जे पूवी शक्य
नव्हते . सखोल र्शक्षणामध्ये , कॉम्प्युटर मॉडे ल प्रर्तमा, मजकूर र्कंवा ध्वनी यावरून थेट वगीकरण काये करण्यास

र्शकते . सखोल र्शक्षण मॉडे ल अत्याधुर्नक अचूकता प्राप्त करू शकतात, काहीवेळा मानवी-स्तरीय कामर्गरीपेक्षा
जास्त. लेबल केलेल्या डे टाचा एक मोठा संच आर्ण अनेक स्तर असलेल्या न्यूरल नेटवकि आर्किटे क्चरचा वापर

करून मॉडे ल प्रर्शर्क्षत केले जातात.

Dept. Of Computer Engineering Page 6

Mahavir Polytechnic CO6I-ETI-UNIT 1

Neural networks: These consist of computer programs that mimic the way the human brain processes
information. They specialize in clustering information and recognizing complex patterns, giving
computers the ability to use more sophisticated processes to analyze data.

न्यूरल नेटवकि, ज्यां ना आर्टि र्फर्शयल न्यूरल नेटवर्क्ि (ANNs) र्कंवा र्सम्युलेटेड न्यूरल नेटवर्क्ि (SNNs) दे खील
म्हणतात, हे मशीन लर्निंगचे एक उपसंच आहे त आर्ण ते सखोल र्शक्षण अल्गोररदमच्या केंद्रस्थानी आहे त. त्यां चे

नाव आर्ण रचना मानवी मेंदूद्वारे प्रेररत आहे त, जैर्वक न्यूरॉन्स एकमेकां ना र्सग्नल करतात त्या मागाि ची नक्कल
करतात.

Components of AI
The core components and constituents of AI are derived from the concept of logic, cognition and
computation; and the compound components, built-up through core components are knowledge,
reasoning, search, natural language processing, vision etc.

Types of Artificial Intelligence:

Artificial Intelligence can be divided in various types, there are mainly two types of main categorization
which are based on capabilities and based on functionally of AI. Following is flow diagram which
explain the types of AI.

AI type-1: Based on Capabilities

Dept. Of Computer Engineering Page 7

 Mahavir Polytechnic CO6I-ETI-UNIT 1

1. Weak AI or Narrow AI:

 Narrow AI is a type of AI which is able to perform a dedicated task with intelligence. The most common
and currently available AI is Narrow AI in the world of Artificial Intelligence.
 Narrow AI cannot perform beyond its field or limitations, as it is only trained for one specific task.
Hence it is also termed as weak AI. Narrow AI can fail in unpredictable ways if it goes beyond its limits.
 Apple Siriis a good example of Narrow AI, but it operates with a limited pre-defined range of functions.
 IBM's Watson supercomputer also comes under Narrow AI, as it uses an Expert system approach
combined with Machine learning and natural language processing.
 Some Examples of Narrow AI are playing chess, purchasing suggestions on e-commerce site, self-
driving cars, speech recognition, and image recognition.

2. General AI:

 General AI is a type of intelligence which could perform any intellectual task with efficiency like a
human.
 The idea behind the general AI to make such a system which could be smarter and think like a human by
its own.
 Currently, there is no such system exist which could come under general AI and can perform any task as
perfect as a human.
 The worldwide researchers are now focused on developing machines with General AI.
 As systems with general AI are still under research and it will take lots of efforts and time to develop
such systems.

3. Super AI:

 Super AI is a level of Intelligence of Systems at which machines could surpass human intelligence, and
can perform any task better than human with cognitive properties. It is an outcome of general AI.
 Some key characteristics of strong AI include capability include the ability to think, to reason,solve the
puzzle, make judgments, plan, learn, and communicate by its own.
 Super AI is still a hypothetical concept of Artificial Intelligence. Development of such systems in real is
still world changing task.

Dept. Of Computer Engineering Page 8

 Mahavir Polytechnic CO6I-ETI-UNIT 1

Artificial Intelligence type-2: Based on functionality

1. Reactive Machines

 Purely reactive machines are the most basic types of Artificial Intelligence.
 Such AI systems do not store memories or past experiences for future actions.
 These machines only focus on current scenarios and react on it as per possible best action.
 IBM's Deep Blue system is an example of reactive machines.
 Google's AlphaGo is also an example of reactive machines.

2. Limited Memory

 Limited memory machines can store past experiences or some data for a short period of time.
 These machines can use stored data for a limited time period only.
 Self-driving cars are one of the best examples of Limited Memory systems. These cars can store recent
speed of nearby cars, the distance of other cars, speed limit, and other information to navigate the road.

3. Theory of Mind

 Theory of Mind AI should understand the human emotions, people, beliefs, and be able to interact
socially like humans.
 This type of AI machines are still not developed, but researchers are making lots of efforts and
improvement for developing such AI machines.

Dept. Of Computer Engineering Page 9

 Mahavir Polytechnic CO6I-ETI-UNIT 1

4. Self-Awareness

 Self-awareness AI is the future of Artificial Intelligence. These machines will be super intelligent, and
will have their own consciousness, sentiments, and self-awareness.
 These machines will be smarter than human mind.
 Self-Awareness AI does not exist in reality still and it is a hypothetical concept.

Following are some key points which show the importance of Machine Learning:

 Rapid increment in the production of data

 Solving complex problems, which are difficult for a human
 Decision making in various sector including finance
 Finding hidden patterns and extracting useful information from data.

Data Visualization

Data visualization is like using pictures or graphs to show information instead of just using words or
numbers. It helps make data easier to understand by turning it into visual representations, like charts,
graphs, or maps. For example, instead of reading a long list of numbers, you can look at a graph or a
chart that shows the same information in a way that's easier to see and understand. It's a way of making
complex information simpler and more accessible by turning it into visual images.

. , ,

, , , .

, ,
. , ,

, .

Dept. Of Computer Engineering Page 10

 Mahavir Polytechnic CO6I-ETI-UNIT 1

, ,

. ,
.

, .

Data types in data visualization

In data visualization, there are several types of data that can be represented visually. Here are some
common data types:

1. Quantitative Data: This type of data represents quantities or numerical values. It can be continuous,
like temperature or height, or discrete, like the number of students in a class. Quantitative data can be
visualized using various types of charts and graphs such as bar charts, line charts, scatter plots,
histograms, and box plots.
2. Categorical Data: Categorical data represents categories or groups. Examples include types of fruits,
colors, or job titles. Categorical data can be visualized using bar charts, pie charts, stacked bar charts,
and frequency tables.
3. Ordinal Data: Ordinal data represents categories with a natural order or ranking. For example, ratings
such as "excellent," "good," "fair," and "poor" have a clear order. Ordinal data can be visualized using
bar charts, stacked bar charts, and dot plots.
4. Time-Series Data: Time-series data represents values collected over a sequence of time intervals.
Examples include stock prices over months, temperature changes over days, or website traffic over
hours. Time-series data is often visualized using line charts, area charts, and stacked area charts.
5. Spatial Data: Spatial data represents information related to geographic locations or regions. It can
include data like population density, rainfall levels, or election results by region. Spatial data is typically
visualized using maps, choropleth maps, heat maps, and cartograms.

Dept. Of Computer Engineering Page 11

 Mahavir Polytechnic CO6I-ETI-UNIT 1

Scales map of data values in aesthetics

In data visualization, scales map data values to aesthetics to visually represent the data effectively. Let's
break it down:

1. Data Values: These are the actual values from your dataset. For example, if you're visualizing sales
data, the data values might be the actual sales numbers for each month.
2. Aesthetics: Aesthetics refer to visual properties such as position, color, size, shape, and texture that you
can use to represent your data visually. For example, you might use position along the x-axis to
represent time (e.g., months) and position along the y-axis to represent sales numbers. Color could be
used to represent different categories or groups within the data.
3. Scales: Scales define the mapping between data values and aesthetics. They define how the range of
data values is translated into the visual range of the aesthetics. For example, a scale might map the range
of sales numbers to the range of positions along the y-axis. Scales also handle transformations such as
logarithmic scaling for better visualization of skewed data distributions.

Use of colors to represent data values

Colors play a crucial role in data visualization by representing different data values, categories, or
patterns. Here's how colors are used:

1. Categorical Data: Different categories or groups within the data can be represented by distinct colors.
For example, if you're visualizing data about different types of fruits, you might use different colors for
apples, oranges, and bananas. This makes it easy to differentiate between categories at a glance,
especially in pie charts, bar charts, and scatter plots.
2. Sequential Data: Sequential data represents a range of values ordered from low to high or vice versa.
Colors can be used to create gradients or shades to represent the magnitude of these values. Lighter
shades might represent lower values, while darker shades represent higher values. This technique is
commonly used in heatmaps, choropleth maps, and line charts to show trends or patterns over time or
space.
3. Diverging Data: Diverging data represents values that diverge from a central point. In this case, colors
can be used to show positive and negative deviations from a midpoint. For example, in a diverging color

Dept. Of Computer Engineering Page 12

 Mahavir Polytechnic CO6I-ETI-UNIT 1

scale, shades of blue might represent negative values, while shades of red represent positive values, with
white or neutral colors indicating the midpoint. This technique is often used in diverging bar charts,
diverging stacked bar charts, and diverging heatmaps.
4. Highlighting Data: Colors can also be used to highlight specific data points or areas of interest within
visualization. By using contrasting colors or brighter hues, you can draw attention to particular elements
of the data, such as outliers, important trends, or specific categories.

Representing - Amounts, Distribution, and Proportions

Representing amounts, distribution, and proportions in data visualization is essential for understanding
patterns, trends, and relationships within the data. Here's how these aspects can be effectively visualized:

1. Amounts:
o Bar Charts: Use horizontal or vertical bars to represent the magnitude of different categories or data
points. The length or height of the bars corresponds to the amount.
o Pie Charts: Use slices of a circle to represent the proportion of each category relative to the whole. The
size of each slice represents the amount or proportion it contributes.
o Treemaps: Divide a rectangular area into smaller rectangles, with each rectangle representing a category
or data point. The size of each rectangle corresponds to the amount.
2. Distribution:
o Histograms: Use bars to represent the frequency or count of data points within predefined intervals or
bins. Histograms show the distribution of continuous data.
o Box Plots: Use boxes and whiskers to display the distribution of data, including measures such as
median, quartiles, and outliers. Box plots provide insights into the spread and central tendency of the
data.
o Kernel Density Estimation (KDE) Plots: Use smoothed curves to estimate the probability density
function of the data. KDE plots provide a smooth representation of the data distribution.
3. Proportions:
o Stacked Bar Charts: Use bars divided into segments to represent proportions of different categories
within each bar. Stacked bar charts show the composition of a whole and the proportion contributed by
each category.

Dept. Of Computer Engineering Page 13

 Mahavir Polytechnic CO6I-ETI-UNIT 1

o Donut Charts: Similar to pie charts but with a hole in the center, donut charts represent proportions of
categories relative to the whole. Each segment represents a proportion, and the size of the segments
indicates the proportion they contribute.

When visualizing amounts, distribution, and proportions, it's important to choose the appropriate type of
visualization based on the nature of the data and the insights you want to convey. Additionally, labeling,
color coding, and providing context are essential for enhancing the interpretability of the visualizations
and facilitating meaningful analysis.

Data Storytelling

Data storytelling is a powerful method of communicating insights derived from data in a compelling and
understandable manner. It involves combining data analysis, visualization, and narrative techniques to
create a cohesive and engaging story that resonates with the audience.
At its core, data storytelling aims to answer questions, convey messages, or drive action through the use
of data-driven evidence presented in a narrative format. Instead of merely presenting raw data or
statistics, data storytelling contextualizes information within a narrative arc, guiding the audience
through a journey of discovery and understanding.
By incorporating elements of storytelling, such as characters, plot, and conflict, data storytelling
humanizes data, making it more relatable and accessible to a wider audience. It enables individuals and
organizations to make informed decisions, solve problems, and drive change based on data-driven
insights.
Data storytelling is increasingly recognized as a crucial skill in various fields, including business,
academia, journalism, and public policy. It empowers individuals to effectively communicate complex
ideas, build persuasive arguments, and inspire action through the power of data-driven storytelling.

Data storytelling is the process of using data and visualizations to convey a narrative or tell a story. It
involves presenting data in a way that engages and resonates with the audience, enabling them to
understand complex information, gain insights, and make decisions. Here's how data storytelling works:

1. Identify the Story: Start by understanding the purpose of your data analysis and identifying the story
you want to tell. What message or insights do you want to communicate to your audience? What
questions are you trying to answer with your data?

Dept. Of Computer Engineering Page 14

 Mahavir Polytechnic CO6I-ETI-UNIT 1

2. Collect and Analyze Data: Gather relevant data that supports your story and analyze it to uncover
insights, trends, patterns, and relationships. Use statistical methods, visualization techniques, and data
exploration to understand the data better.
3. Create Visualizations: Select appropriate visualizations, such as charts, graphs, maps, and infographics,
to represent your data effectively. Choose visuals that highlight key findings and make complex
information easy to understand. Ensure that your visualizations are clear, concise, and visually
appealing.
4. Craft the Narrative: Develop a compelling narrative that guides the audience through your data story.
Structure your story with a clear beginning, middle, and end. Introduce the context and background,
present the main findings and insights, and conclude with actionable recommendations or implications.
5. Engage the Audience: Use storytelling techniques, such as anecdotes, examples, and real-world
scenarios, to engage the audience emotionally and intellectually. Tailor your story to the interests,
knowledge level, and needs of your audience. Invite interaction and encourage questions and discussion
to deepen understanding and engagement.
6. Provide Context and Interpretation: Offer context, explanations, and interpretations to help the
audience understand the significance of the data and its implications. Highlight key trends, outliers, and
insights, and explain their implications for decision-making or problem-solving.
7. Empower Action: Conclude your data story by empowering the audience to take action based on the
insights you've presented. Provide clear recommendations, next steps, or calls to action that encourage
the audience to apply the insights from the data to their own work or decision-making.

Overall, effective data storytelling combines data analysis, visualization, and narrative techniques to
create a compelling and impactful story that educates, informs, and inspires action. It bridges the gap
between data and understanding, helping organizations and individuals make informed decisions and
drive positive change.

Dept. Of Computer Engineering Page 15

 Mahavir Polytechnic CO6I-ETI-UNIT 1

, .

.
:

1. :

. ? ?
?

2. :
.

3. : , , , , ,
. ,

.
4. : .

5. :
. , ,

.
6. :

Data storytelling is a powerful method of communicating insights derived from data in a

compelling and understandable manner. It involves combining data analysis, visualization, and narrative
techniques to create a cohesive and engaging story that resonates with the audience.
At its core, data storytelling aims to answer questions, convey messages, or drive action through the use
of data-driven evidence presented in a narrative format. Instead of merely presenting raw data or
statistics, data storytelling contextualizes information within a narrative arc, guiding the audience
through a journey of discovery and understanding.

Dept. Of Computer Engineering Page 16

 Mahavir Polytechnic CO6I-ETI-UNIT 1

By incorporating elements of storytelling, such as characters, plot, and conflict, data storytelling
humanizes data, making it more relatable and accessible to a wider audience. It enables individuals and
organizations to make informed decisions, solve problems, and drive change based on data-driven
insights.
Data storytelling is increasingly recognized as a crucial skill in various fields, including business,
academia, journalism, and public policy. It empowers individuals to effectively communicate complex
ideas, build persuasive arguments, and inspire action through the power of data-driven storytelling.

Ineffectiveness of Graphical representation of data in data storytelling

While graphical representation of data is a powerful tool in data storytelling, there are instances where it
may be ineffective or misleading. Here are some scenarios where graphical representation may fall short
in data storytelling:

1. Misleading Visualizations: Graphical representations can sometimes distort or misrepresent data if not
designed and interpreted carefully. For example, improper scaling, inappropriate chart types, or selective
data presentation can lead to misinterpretation of the data.
2. Overly Complex Visuals: Complex visualizations with too much information or cluttered design can
overwhelm the audience and detract from the main message. It's essential to keep visualizations clear,
concise, and focused on conveying key insights without unnecessary complexity.
3. Lack of Context: Graphical representations may lack context or fail to provide sufficient background
information to help the audience understand the significance of the data. Without proper context,
visualizations may be open to misinterpretation or lead to incomplete understanding.
4. Audience Understanding: Some audience members may have difficulty interpreting graphical
representations, particularly if they lack familiarity with data visualization techniques or if the visuals
are overly technical. It's essential to consider the audience's level of understanding and tailor
visualizations accordingly.
5. Emotional Impact: Graphical representations may lack the emotional impact or storytelling elements
needed to engage and resonate with the audience on a deeper level. While visuals can convey
quantitative information effectively, they may not always evoke the desired emotional response or
connection.

Dept. Of Computer Engineering Page 17

 Mahavir Polytechnic CO6I-ETI-UNIT 1

6. Cultural and Linguistic Factors: Graphical representations may not always translate effectively across
different cultural or linguistic contexts. Symbols, colors, and visual metaphors may have different
meanings or interpretations in different cultures, leading to potential misunderstandings.

Explanatory Analysis Who, What, How

In data storytelling, explanatory analysis focuses on answering key questions about the data: Who,
What, and How. Here's how these elements contribute to effective data storytelling:

1. Who:
o This aspect of explanatory analysis focuses on understanding the audience or stakeholders who will be
consuming the data story. Who are they? What are their roles, backgrounds, and interests?
Understanding the audience helps tailor the storytelling approach, language, and visualizations to ensure
maximum relevance and engagement.
o For example, if the audience consists of executives, they may be more interested in high-level
summaries and strategic insights, while analysts may require more detailed technical explanations and
interactive visualizations.
2. What:
o This component involves identifying the key messages, insights, or findings that the data story aims to
communicate. What is the main story or narrative? What are the key points that need to be conveyed to
the audience? Defining the "what" helps ensure clarity and focus in the storytelling process.
o For instance, if analyzing sales data, the main message might be identifying trends in sales performance,
highlighting top-performing products or regions, or uncovering factors influencing customer behavior.
3. How:
o The "how" aspect focuses on the methods and techniques used to analyze and visualize the data
effectively. How was the data collected, processed, and analyzed? How are the findings presented to the
audience? The "how" helps ensure that the data story is based on sound analytical approaches and that
the visualizations are clear, accurate, and impactful.
o This may involve selecting appropriate data visualization techniques, such as charts, graphs, or maps,
and employing storytelling techniques, such as narrative structure, visualization design principles, and
interactive features.

Dept. Of Computer Engineering Page 18

Mahavir Polytechnic CO6I-ETI-UNIT 1

By addressing the Who, What, and How of data storytelling, explanatory analysis helps create
compelling and informative narratives that resonate with the audience, convey meaningful insights, and
drive informed decision-making. It ensures that the data story is tailored to the needs and preferences of
the audience, grounded in rigorous analysis, and effectively communicated through clear and engaging
storytelling techniques.

How does Machine Learning work

A Machine Learning system learns from historical data, builds the prediction models, and
whenever it receives new data, predicts the output for it. The accuracy of predicted output depends
upon the amount of data, as the huge amount of data helps to build a better model which predicts the
output more accurately.

Suppose we have a complex problem, where we need to perform some predictions, so instead of writing
a code for it, we just need to feed the data to generic algorithms, and with the help of these algorithms,
machine builds the logic as per the data and predict the output. Machine learning has changed our way
of thinking about the problem. The below block diagram explains the working of Machine Learning
algorithm:

ए
- . , ,
. , ,
- . ,
.

Dept. Of Computer Engineering Page 19

 Mahavir Polytechnic CO6I-ETI-UNIT 1

Classification of Machine Learning

At a broad level, machine learning can be classified into three types:

1. Supervised learning
2. Unsupervised learning
3. Reinforcement learning

1) Supervised Learning

Supervised learning is a type of machine learning method in which we provide sample labeled data to
the machine learning system in order to train it, and on that basis, it predicts the output.

The system creates a model using labeled data to understand the datasets and learn about each data, once
the training and processing are done then we test the model by providing a sample data to check whether
it is predicting the exact output or not.

The goal of supervised learning is to map input data with the output data. The supervised learning is
based on supervision, and it is the same as when a student learns things in the supervision of the teacher.
The example of supervised learning is spam filtering.

2) Unsupervised Learning

Unsupervised learning is a learning method in which a machine learns without any supervision.

Dept. Of Computer Engineering Page 20

 Mahavir Polytechnic CO6I-ETI-UNIT 1

The training is provided to the machine with the set of data that has not been labeled, classified, or
categorized, and the algorithm needs to act on that data without any supervision. The goal of
unsupervised learning is to restructure the input data into new features or a group of objects with similar
patterns.

In unsupervised learning, we don't have a predetermined result. The machine tries to find useful insights
from the huge amount of data. It can be further classifieds into two categories of algorithms:

 Clustering
 Association

3) Reinforcement Learning

Reinforcement learning is a feedback-based learning method, in which a learning agent gets a reward for
each right action and gets a penalty for each wrong action. The agent learns automatically with these
feedbacks and improves its performance. In reinforcement learning, the agent interacts with the
environment and explores it. The goal of an agent is to get the most reward points, and hence, it
improves its performance.

The robotic dog, which automatically learns the movement of his arms, is an example of Reinforcement
learning.

Application of AI

Artificial Intelligence has various applications in today's society. It is becoming essential for today's
time because it can solve complex problems with an efficient way in multiple industries, such as
Healthcare, entertainment, finance, education, etc. AI is making our daily life more comfortable and fast.

Dept. Of Computer Engineering Page 21

 Mahavir Polytechnic CO6I-ETI-UNIT 1

1. 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.

2. AI in Healthcare

 In the last, five to ten years, AI becoming more advantageous for the healthcare industry and going to
have a significant impact on this industry.
 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.

3. 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.

Dept. Of Computer Engineering Page 22

 Mahavir Polytechnic CO6I-ETI-UNIT 1

4. 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.

5. AI in Data Security

 The security of data is crucial for every company and cyber-attacks are growing very rapidly in the
digital world. 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.

6. 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. AI can organize and manage massive amounts of data.
AI can analyze lots of data to identify the latest trends, hashtag, and requirement of different users.

7. AI in Travel & Transport

 AI is becoming highly demanding for travel industries. AI is capable of doing various travel related
works such as from making travel arrangement to suggesting the hotels, flights, and best routes to the
customers. Travel industries are using AI-powered chatbots which can make human-like interaction with
customers for better and fast response.

8. 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.
 Various Industries are currently working for developing self-driven cars which can make your journey
more safe and secure.

Dept. Of Computer Engineering Page 23

 Mahavir Polytechnic CO6I-ETI-UNIT 1

9. 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 Robots are best examples for AI in robotics, recently the intelligent Humanoid robot named
as Erica and Sophia has been developed which can talk and behave like humans.

10. 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.

11. AI in Agriculture

 Agriculture is an area which requires various resources, labor, money, and time for best result. Now a
day's agriculture is becoming digital, and AI is emerging in this field. Agriculture is applying AI as
agriculture robotics, solid and crop monitoring, predictive analysis. AI in agriculture can be very helpful
for farmers.

12. 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.

13. 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.
 AI in the future can be work as a personal virtual tutor for students, which will be accessible easily at
any time and any place.

Dept. Of Computer Engineering Page 24

Mahavir Polytechnic CO6I-ETI-UNIT 1

Dept. Of Computer Engineering Page 25