ARTIFICIAL INTELLIGENCE

AI is intelligence demonstrated by machines

Disclaimer: The content is curated for educational purposes only.

© Edunet Foundation. All rights reserved.
Agenda
● Introduction to AI
● History of AI and Market Trends
● Machine Learning and Types of Machine Learning
● Data Analysis
● Python Basics
● NumPy and Matplotlib

© Edunet Foundation. All rights reserved.

 Pre-Requisites
1. Anaconda
https://www.anaconda.com/products/individual-d

2. LMS
https://lms.techsaksham.org/

© Edunet Foundation. All rights reserved.

What is Artificial Intelligence?

https://en.wikiversity.org/wiki/Artificial_intelligence/Introduction

© Edunet Foundation. All rights reserved.

Introduction of Artificial Intelligence
Intelligence : “The capacity to learn and solve problems.”

Artificial Intelligence : AI is the simulation of

human intelligence by machines.

1) The ability to think rationally.

2) The ability to think like humans.
3) The ability to act rationally.
4) The ability to act like humans.

https://www.tu-berlin.de/menue/summer_university/old_versions/winter_university/introduction_to_artificial_intelligence

© Edunet Foundation. All rights reserved.

Classification of AI
Artificial Intelligence

Narrow AI General AI
• Performs Repetitive Tasks • Performs a multitude of tasks
• Limited Ability • Unlimited Abilities
• Cannot self-program • Can self-program
• Currently Existent • Currently inexistent

© Edunet Foundation. All rights reserved.

The conference that started it all: Dartmouth Summer Research Project on
Artificial Intelligence organized by John McCarthy

• The 1950s – Artificial Intelligence was

born: first artificial intelligence program which
was named as "Logic Theorist"
• Late 1960s to 1970s - The First AI Winter
• Early 1980s - The AI Boom due to development
of learning techniques
• Late 1980s to 1990s - The Second AI Winter
• Late 1990s to 2000s - Renewed success in
various fields.
• 2010s to Present - Modern AI with cutting edge
solutions in all walks of life

@Edunet © Edunet Foundation.

Foundation, All rightsAll rights reserved.
reserved
Common Use cases

© Edunet Foundation. All rights reserved.

 Applications of AI
• Healthcare

• Automobile

• Finance

• Social Media

• Education

• E-commerce

© Edunet Foundation. All rights reserved.

Market opportunities and career in AI

Source - https://www.tractica.com/

© Edunet Foundation. All rights reserved.

AI Subdomains

https://static.javatpoint.com/tutorial/ai/images/subsets-of-ai.png
© Edunet Foundation. All rights reserved.
AI vs ML vs DL

https://docs.microsoft.com/en-us/azure/architecture/data-guide/big-data/ai-overview
© Edunet Foundation. All rights reserved.
Machine Learning
Machine Learning gives computers the capability to learn from data, improve its
performance with experiences, and predict things without being explicitly
programmed.

https://static.javatpoint.com/tutorial/machine-learning/images/introduction-to-machine-learning2.png

© Edunet Foundation. All rights reserved.

 Classification of Machine Learning

https://social.technet.microsoft.com/wiki/cfs-filesystemfile.ashx/__key/communityserver-wikis-components-files/00-
00-00-00-05/7002.5_5F00_1.PNG
© Edunet Foundation. All rights reserved.
Pipeline of Machine Learning

https://www.xenonstack.com/blog/machine-learning-pipeline/
© Edunet Foundation. All rights reserved.
PRACTICAL : Image Recognition on Microsoft Lobe

https://lobe.ai/
© Edunet Foundation. All rights reserved.
 Data Analysis

https://www.import.io/post/business-data-analysis-what-how-why/

© Edunet Foundation. All rights reserved.

What is Data Analysis ?
• The process of cleaning, analysing, interpreting, and visualizing data
to discover valuable insights that drive smarter and more effective
business decisions

• It is the process of systematically applying statistical and/or

logical techniques to describe and illustrate, condense and recap, and
evaluate data

© Edunet Foundation. All rights reserved.

https://careerfoundry.com/en/blog/data-analytics/the-data-analysis-process-step-by-step/
© Edunet Foundation. All rights reserved.
Types of Data Analysis
• Descriptive Analysis: It tries to understand what happened in the
past by analysing the stored data.

• Diagnostic Analysis: It focuses on understanding why something has

happened. It is literally the diagnosis of a problem

• Predictive Analysis: It tries to understand what could happen in the

future using past data analysis.

• Prescriptive Analysis: It allows you to make recommendations for

the future. This is the final step in the analytics part of the process.

© Edunet Foundation. All rights reserved.

Data Analysis Tools
Many tools are available in the market, which make it easier for us:

1. To process and manipulate data

2. Analyse the relationships and correlations between data sets,​
3. Helps to identify patterns and trends for interpretation

© Edunet Foundation. All rights reserved.

PYTHON BASICS

© Edunet Foundation. All rights reserved.

What is Python?

• Python is a General-Purpose, high-level Programming language.

• Python is also an interpreter language, i.e., does not need

compilation before execution

• It was created by Guido van Rossum in 1991 and was designed with an
emphasis on code readability.

© Edunet Foundation. All rights reserved.

Python is easy to learn

Java

Python

© Edunet Foundation. All rights reserved.

Python - Uses

WEB SOFTWARE MATHEMATICS DATA SCIENCE

DEVELOPMENT DEVELOPMENT

© Edunet Foundation. All rights reserved.

Variables
Variables in python as
the name suggests are
the values that vary
Variables are containers for storing
data values
A Variable in python is
created as soon as a
value is assigned to it

© Edunet Foundation. All rights reserved.

Variable Name

• Should start with letter (a-z A-Z) or underscore (_).

• Case sensitive, Numbers not allowed at the beginning.

• Name should not be a Python keyword.

© Edunet Foundation. All rights reserved.

What are the Datatypes in Python?
• Numeric

• Sequence Type

• Boolean

• Set

• Dictionary

http://www.javatpoint.com/python-data-types
© Edunet Foundation. All rights reserved.
Controls Structures in python?

https://microbit-challenges.readthedocs.io/en/latest/_images/control_structures_diagram.png
© Edunet Foundation. All rights reserved.
Decision Making Statements in Python?

https://techvidvan.com/tutorials/wp-content/uploads/sites/2/2019/12/Decision-Making-in-Python.jpg
© Edunet Foundation. All rights reserved.
Loops in Python?

https://techvidvan.com/tutorials/wp-content/uploads/sites/2/2019/12/Decision-Making-in-Python.jpg
© Edunet Foundation. All rights reserved.
Loops Controls in Python?

https://techvidvan.com/tutorials/wp-content/uploads/sites/2/2020/01/loop-control-statement-in-python.jpg
© Edunet Foundation. All rights reserved.
Python Libraries
• Python Libraries are a set of useful functions that eliminate the need for
writing codes from scratch

• There are over 137,000 python libraries present today

• Python libraries play a vital role in developing machine learning, data science,
data visualization, image and data manipulation applications and more

© Edunet Foundation. All rights reserved.

 Python Libraries

NumPy

OpenCV

Pandas
Scikit Learn

TensorFlow
Keras
© Edunet Foundation. All rights reserved.
NUMPY LIBRARY

Disclaimer: The content is curated for educational purposes only.

© Edunet Foundation. All rights reserved.
Introduction
• NumPy is an open-source Python library used for working with arrays

• NumPy stands for Numerical Python

• The NumPy array is a data structure that efficiently stores and accesses
multidimensional arrays

• NumPy is a Python library and is written partially in Python, but most of the
parts that require fast computation are written in C or C++

© Edunet Foundation. All rights reserved.

Installing NumPy Module
• You may use Command Prompt/Terminal

• You need pip/conda to install various libraries

pip install numpy
conda install numpy

Note: It is pre-installed if Anaconda Software is used

© Edunet Foundation. All rights reserved.
Why NumPy?

© Edunet Foundation. All rights reserved.

Practicals on NumPy
• Creating Numpy Array of different dimensions (Scalars vs Vectors vs
Matrices)
• Random Generator Number
• Importance of Random Seed
• Matrix Multiplication in Numpy
• Descriptive Statistics using Numpy
• Interquartile Range
• Broadcasting in Numpy
• How to sort Numpy Arrays?

© Edunet Foundation. All rights reserved.

Statistical Functions on Arrays

© Edunet Foundation. All rights reserved.

Broadcasting of an Array
a 0 1 2 3 4

10 10 10 10 10 c = a + 10

c 10 11 12 13 14
14

© Edunet Foundation. All rights reserved.

Broadcasting of an Array
0 1 10 10 0 11
2 3 + 20 20 = 22 23
4 5 30 30 34 35

a b c

© Edunet Foundation. All rights reserved.

Sorting an Array

© Edunet Foundation. All rights reserved.

Data Visualization
The way of Reading Data in a Visual form

© Edunet Foundation. All rights reserved.

What is Data Visualization?

Data visualization deals with a visual

representation of data and is part of
data analysis. It is the process of
translating data into a chart, graph, or
other visual components.

https://www.techfunnel.com/wp-content/uploads/2020/10/data-visualization.png

© Edunet Foundation. All rights reserved.

Plotting and Visualization
Data visualization packages and tools are required to provide an accessible
way to analyze massive amounts of information and understand trends and
patterns in data.

© Edunet Foundation. All rights reserved.

Matplotlib

Matplotlib is one of the most popular Python packages used for data
visualization. It is a cross-platform library for making 2D plots from data in
arrays.

© Edunet Foundation. All rights reserved.

Line Plot
According to the wiki,

“A line chart or line plot or

line graph is a type of
chart which displays
information as a series of
data points called
‘markers’ connected by
straight line segments. It
is a basic type of chart
common in many fields”

https://medium.com/@patrickbfuller/line-plot-7b4068a3a9fc
© Edunet Foundation. All rights reserved.
Bar Plot
A bar chart or bar graph is a chart or
graph that presents categorical data
with rectangular bars with heights or
lengths proportional to the values that
they represent. The bars can be plotted
vertically or horizontally.

Syntax:

ax.bar(x, height, width, bottom, align)

plt.bar(x,y)
© Edunet Foundation. All rights reserved.
 Scatter Plot
A scatter plot is a diagram where
each value in the data set is
represented by a dot.

Use the scatter() method to draw a

scatter plot diagram:

Syntax:

plt.scatter(x, y)

© Edunet Foundation. All rights reserved.

3-D Plotting in Matplotlib
• Three-dimensional plots are enabled by
importing the mplot3d toolkit, included
with the main Matplotlib installation:
• from mpl_toolkits import mplot3d

• Syntax:
plt.plot3D()

https://jakevdp.github.io/PythonDataScienceHandbook/04.12-three-dimensional-plotting.html
© Edunet Foundation. All rights reserved.
Pie Chart
• Matplotlib API has pie() function in
its pyplot module which creates a pie
chart representing the data in an
array.

• Syntax:
plt.pie(data)

https://www.geeksforgeeks.org/plot-a-pie-chart-in-python-using-matplotlib/

© Edunet Foundation. All rights reserved.

 REFERENCES
1.Public information, Deloitte Research
2.http://www.oreilly.com/data/free/the-new-artificial-intelligence-market.csp
3.https://www.weforum.org/agenda/2018/09/artificial-intelligence-shaking-up-
job-market/
4.https://en.wikiversity.org/wiki/Artificial_intelligence/Introduction
5.https://techvidvan.com/tutorials/artificial-intelligence-applications/
6.https://www.xenonstack.com/blog/machine-learning-pipeline/
7.https://docs.microsoft.com/en-us/azure/architecture/data-guide/big-data/ai-
overview
8.https://www.javatpoint.com/history-of-artificial-intelligence
Disclaimer: The content is curated for educational purposes only.
© Edunet Foundation. All rights reserved.
THANK YOU

© Edunet Foundation. All rights reserved.