Unit -1

Artificial
intelligence
Course Outcome
Describe Artificial Intelligence, Machine
learning and deep learning, Data visualization
and Data storytelling.
AI =

“Artificial can be considered as Man

Made” & “Intelligence is commonly
considered as
the ability to collect knowledge to solve
complex problems”
• Its an approach
to make a computer, a robot or a product to think how smart human think.
• Its a study of
how human brain think, learn, decide and work, when it tries to solve problems.

The science and engineering of making intelligent machines, especially intelligent

computer programs
– John McCarthy
 Concept of AI
• Concept of Artificial intelligence (AI)
• Artificial intelligence (AI) is the simulation of human intelligence
processes by machines, especially computer systems.

Particular applications of AI include

Expert systems :- An expert system is a computer program that uses
artificial intelligence (AI) technologies to simulate the judgment and
behavior of a human or an organization that has expert knowledge and
experience in a particular field.
Speech recognition:- Voice recognition systems enable consumers to
interact with technology simply by speaking to it.
Machine vision:- Machine vision is the ability of a computer to see; it
employs one or more video cameras, analog-to-digital conversion (ADC) and
digital signal processing (DSP). The resulting data goes to a computer or
robot controller.
lving
Scope of AI
In the field of education

• Artificial intelligence can automate basic activities in education like grading,

• Educational software can be adapted to student needs.
• It can point out places where courses need to improve
• Students could get additional support from AI tutors.
• AI-driven programs can give students and educators helpful feedback.

itng
• Problem solving
Ability to formulate a problem in a suitable representation, to plan or its solution and
to know when new information is needed and how to obtain it.

Inference (Resolution-Based Theorem Proving)

–Interactive Problem Solving
–Automatic Program Writing
–Heuristic Search

cont.
ces o cusom
Robots

– Exploration
– Transportation/Navigation
– Industrial Automation (e.g., Process Control, Assembly Tasks, Executive Tasks)
• Security
• Other (Agriculture, Fishing, Mining, Sanitation, Construction, etc.)
• Military
• Household
• Other (Agriculture, Fishing, Mining, Sanitation, Construction, etc.)
• Military
• Household
• Games
• For emergency services
• For Entertainment
• For providing services to customers
 Components of AI
Level Core Compound Coarse components
Induction
Logic Proposition Knowledge Knowledge based
Tautology Reasoning systems, Heuristic
Model Logic Control Search Theorem
Search Proving
Temporal Multi Agent system
Cognitio Learning Belief Desire Co-operation, Co-
n Adaptation Intention ordination AI
Self- Programming
organization
Vision
Functio Memory Utterance Natural Language
nal Perception Speech Processing
Types of AI
Application of AI
 Data Visualization
• Definition: The graphical representation of data to
help users understand patterns, trends, and outliers.
• Importance:
Simplifies complex data
Highlights key insights
Aids in decision-making
Enhances storytelling
 Why is Data Visualization
Important?
• Key Points:
• Makes data more accessible and understandable
• Helps identify trends and patterns quickly
• Assists in presenting data in a more persuasive and
compelling way
• Supports faster decision-making
• Facilitates better communication across teams
 Data Types in Data Visualization
Definition: Data types refer to the kind of data being visualized
and influence the choice of visualization techniques.

1. Categorical Data- Categories with a defined order (e.g., education levels, customer
satisfaction ratings).
2. Numerical Data-Countable numbers (e.g., number of people).
3. Time Series Data-Data collected or recorded at regular time intervals. (eg.line chart
showing sales over a year).
4. Geospatial Data-Data representing locations or geographic features.(eg. Maps)
5. Text Data-Unstructured data involving words or strings(eg. customer feedback)
6. Boolean Data-Binary data indicating two possible outcomes (True/False, Yes/No).
7. Hierarchical Data-Data organized in a tree-like structure with parent-child
relationships(eg. Tree maps)
8. Relational Data-: Data showing relationships between variables or entities.(eg.
network graph showing connections between people or items.)
Types of Example Appropriate Description
Variables Scale
Quantitative/ 1.3, 5.7, 83, Arbitrary numerical values. These
1.5 ×10–2 Continuous
numerical can be integers, rational numbers, or
continuous real numbers.
Quantitative/ Numbers in discrete units. These are
numerical discrete most commonly but not necessarily
1, 2, 3, 4 Discrete integers. For example, the numbers
0.5, 1.0, 1.5 could also be treated as
discrete if intermediate values
cannot exist in the given dataset.
Qualitative/ Categories without order. These are
categorical discrete and uniquecategories that
unordered dog, cat, fish Discrete have no inherent
order. These variables are also called
factors.
Qualitative/ Categories with order. These are
categorical ordered discrete and unique categories with
good, fair, Discrete an order. For example, “fair” always
poor lies between
The quick “good” and “poor.” These variables
Text brown fox None, or are also called
Free-form text.ordered factors.as
Can be treated
Jan. 5 2018,
jumps over the Continuous
discrete Specific days
categorical if and/or
needed.times. Also,
Date or time 8:03am
lazy dog. or generic dates, such as July 4 or Dec.
Discrete 25 (without year).
First 8 rows of a dataset listing daily temperature normal for four
weather stations

Month Day Location Section ID Temperature

(F)
Jan 1 Chicago USW000148 25.6
19
Jan 1 San Diego USW000931 55.2
07
Jan 1 Houston USW000129 53.9
18
Jan 1 Death USC0004231 51.0
Valley 9
Jan 2 Chicago USW000148 25.5
19
Jan 2 San Diego USW000931 55.3
07
Jan 2 Houston USW000129 53.8
18
Jan 2 Death USC0004231 51.2
Valley 9
Fig.The data representation of the above-mentioned example
Fig. Monthly normal mean temperatures for the same example
 Use of Coordinate Systems in Data Visualization
 To explore how coordinate systems are used in data visualization to represent
relationships and trends.
Types of Coordinate Systems:
 Cartesian Coordinate System (most common)
 Polar Coordinate System
 Geographic Coordinate System (for maps)

How They Help:

Multi-Dimensional Data: Using 2D or 3D axes, coordinate systems

can represent multiple variables in a single view.
Common Visualizations Using Coordinate Systems:
Scatter Plots (Cartesian): Show the relationship between two
variables.
Line Graphs (Cartesian): Visualize trends over time or other
continuous variables.
Maps (Geographic): Plot data points on geographic regions using
latitude and longitude.
Fig.Cartesian coordinate system's sample example
Fig. Daily temperature normals for Huston using different aspect ratio
 The Use of Colors to Represent Data

 Color as a Communication Tool:

o Visual Clarity: Color can help distinguish
different data series, highlight key patterns,
and guide viewers’ attention.
o Emotional Impact: Color choices can
influence how data is perceived, evoking
emotions like urgency (red) or calm (blue).
o Categorical and Quantitative Data: Color
helps distinguish between categories or
represent continuous variables
Figure. Representing data using various colors to distinguish regions
Figure . Example sequential color scales.
 Representing - Amounts, Distributions and Proportions in
Data Visualization
Representing Amounts
 Definition: Amounts are the total or sum of data points, representing quantities like sales, population,
or revenue.

Common Visualizations:
• Bar Charts
• Column Charts
• Line Graphs
• Area Charts
 Amounts

The most common approach to visualizing amounts (i.e., numerical values

shown for some set of categories) is using bars, either vertically or horizontally.
If there are two or more sets of categories for which we want to show amounts, we can group
or stack the bars.
Distributions

Histograms and density plots provide the most intuitive visualizations of a distribution
• Boxplots, violin plots, strip charts, and since plots are useful when we want to visualize many
distributions at once.
• Stacked histograms and overlapping densities allow a more in-depth comparison of a smaller
number of distributions.
• Ridgeline plots can be a useful alternative to violin plots and are often useful when visualizing
very large numbers of distributions or changes in distributions over.
 Proportions

Proportions can be visualized as pie charts, side-by-side bars, or stacked bars.

 Data Storytelling

 Definition: Data storytelling is the practice of combining data, visualizations,

and narrative to tell a story that drives insights and facilitates decision-making.
 Key Components:
o Data: The raw information or facts.
o Visuals: Graphs, charts, and other visual aids to represent the data.
o Narrative: A clear story or context that explains the significance of the data.
 Example: A story about sales performance, with charts showing revenue growth
over time, and a narrative explaining factors driving that growth.
Data storytelling is the concept of building a compelling narrative based on
complex data and analytics that help tell your story and influence and inform a
particular audience.

The benefits of data storytelling

✔ Adding value to your data and insights.

✔ Interpreting complex information and highlighting essential key points for the
audience.
✔ Providing a human touch to your data.
✔ Offering value to your audience and industry.
✔ Building credibility as an industry and topic thought leader.
 Elements of Data Storytelling
 The three key elements of data storytelling
Build your narrative
As you tell your story, you need to use your data as supporting pillars
to your insights. Help your audience understand your point of view by
distilling complex information into informative insights.

Use visuals to enlighten

Visuals can help educate the audience on your theory. When you
connect the visual assets (charts, graphs, etc.) to your narrative, you
engage the audience with otherwise hidden insights that provide the
fundamental data to support your theory.

Show data to support

Your narrative offers enlightenment, supported by tangible data.
Context and critique are integral to the full interpretation of your
narrative. Using business analytic tools to provide key insights and
understanding to your narrative can help provide the much-needed
context throughout your data story.
Explanatory Analysis: Uncovering Insights from Data
 Definition: Explanatory analysis is a type of data analysis focused on
explaining the causes and reasons behind observed patterns or trends in the
data.

 Comparison:
o Descriptive Analysis: Summarizes data (What happened?).
o Predictive Analysis: Predicts future outcomes (What could happen?).
o Explanatory Analysis: Explains the reasons behind trends and
relationships (Why did this happen?).
Explanatory Analysis
Explanatory analysis, there are a few things to think about and be extremely clear on before
visualizing any data or creating content. First, to whom are you communicating?
Who -
Your audience - The more specific you can be about who your audience is, the better position you
will be in for successful communication.
You - It’s also helpful to think about the relationship that you have with your audience and how you
expect that they will perceive you.
What-
Action - You should always want your audience to know or do something.
Mechanism - How will you communicate to your audience?

HOW
Data becomes supporting evidence of the story you will build and tell.
 Machine Learning
 Definition: Machine learning is a branch of science that deals with programming the systems in
such a way that they automatically learn and improve with experience.
 Types of Machine Learning:
o Supervised Learning: The model is trained using labeled data (input-output pairs).

eg- classifying email as spam.

o Unsupervised Learning: The model finds hidden patterns or structures in input data without
labels. Common approaches to unsupervised learning include:
• k-means
• self-organizing maps, and
• hierarchical clustering
o Reinforcement Learning: The model learns by interacting with an environment and
receiving feedback (rewards or penalties).
Types of Machine Learning
Reinforcement learning
example
Key Concepts in Machine Learning
 Algorithms: Mathematical methods that ML systems use to learn
from data (e.g., Linear Regression, Decision Trees, K-Means).
 Features: Input variables that provide information to the model.
 Training: The process of teaching a machine learning model using
data.
 Testing: Evaluating the model's performance on new, unseen data.
 When Do We Use Machine Learning?
• ML is used when:
• Human expertise does not exist (navigating on Mars)
• Humans can’t explain their expertise (speech recognition)
• Models must be customized (personalized medicine)
• Models are based on huge amounts of data (genomics)
What is Deep Learning?
 Definition: Deep Learning is a subset of Machine Learning that uses neural networks
with many layers (also known as deep neural networks) to model complex patterns in
large datasets.
 Deep learning is a subfield of machine learning where concerned
algorithms are inspired by the structure and function of the brain called
artificial neural networks
 Key Feature: DL models can automatically extract features from raw data (e.g., images,
audio), making them ideal for tasks like image recognition, natural language processing,
and autonomous driving.
 Visual Example: A diagram of a neural network with multiple layers showing how data
is passed through the network.
Key Concepts in Deep Learning
 Neural Networks: Computational models inspired by the human brain, consisting
of layers of nodes (neurons).
 Layers:
o Input Layer: The first layer, where data enters.

o Hidden Layers: Layers between input and output where complex

transformations occur.
o Output Layer: The final layer that produces the output of the network.
Deep learning Process
Deep learning
example
Key Applications of Machine Learning
 1. Predictive Analytics:
o Example: Predicting customer churn, stock prices, or disease outbreaks.
 2. Natural Language Processing (NLP):
o Example: Spam email filtering, sentiment analysis, chatbots.
 3. Computer Vision:
o Example: Object recognition in images, facial recognition, autonomous vehicles.
 4. Recommender Systems:
o Example: Product recommendations on e-commerce sites (e.g., Amazon), movie
recommendations (e.g., Netflix).
 Visual Example: Examples of ML applications in different industries (e.g., healthcare,
finance, e-commerce).
Key Applications of Deep Learning
 1. Image Recognition and Classification:
o Example: Facial recognition, object detection (e.g., identifying cars in traffic images).
 2. Speech Recognition:
o Example: Voice assistants (e.g., Siri, Alexa), transcription services.
 3. Natural Language Processing:
o Example: Machine translation (e.g., Google Translate), sentiment analysis.
 4. Autonomous Vehicles:
o Example: Self-driving cars using deep neural networks for perception and decision-
making.
 Visual Example: Diagram showing how deep learning powers autonomous vehicle systems
(perception, planning, and control).