The document discusses the importance of machine learning and AI, their applications, and the relationship between data science and AI, along with various tools and frameworks used in these fields. It provides in-depth explanations of machine learning concepts, including regression models and decision trees, as well as a brief overview of deep learning methods and their mathematical foundations. Additionally, it highlights the growing opportunities for data analytics professionals in light of increasing data generation and business awareness.

1. Data Science and Machine Learning with Tensorflow
Shubham Sharma
Data Scientist

2. Agenda
• Importance of Machine Learning and AI – Emerging applications, end-use
• Pictures (Amazon recommendations, Driverless Cars)
• Relationship betweeen Data Science and AI .
• Overall structure and components
• What tools can be used – technologies, packages
• List of tools and their classification
• List of frameworks
• Artificial Intelligence and Neural Networks
• Basics Of ML,AI,Neural Networks with implementations
• Machine Learning Depth : Regression Models
• Linear Regression : Math Behind
• Non Linear Regression : Math Behind
• Machine Learning Depth : Classification Models
• Decision Trees : Math Behind
• Deep Learning
• Mathematics Behind Neural Networks
• Terminologies
• What are the opportunities for data analytics professionals

3. Machine Learning and AI– Everywhere!
Driver Less Cars

4. Relationship betweeen Data Science and AI
• Data Management
• Data Warehousing
• Large scale
computing
• Rule setting
• Knowledge discovery
• Gathering Data
• Statistical analysis
• Data modelling
• AI and ML
• Business Intelligence
• Data interpretation
• Dashboards
Data
Visualization
Data
Analysis and
AI
Data
Engineering
Data Mining

5. Relationship betweeen Data Science and AI– Key Structures

6. Machine Learning and AI Tools,Frameworks
Data Analysis and AI
• Python
• R
• Tensorflow
• Keras
• NumPy
• Pandas
• Scikit-learn
• OpenNLP
• Mahout
• +many others
Data Engineering
• SQL-based technologies
(e.g. PostgreSQL and
MySQL)
• NoSQL technologies (e.g.
Cassandra and MongoDB)
• Hadoop-based
technologies (e.g.
MapReduce, Hive and Pig)
• Data modeling tools (e.g.
ERWin, Enterprise
Architect and Visio)
Data Visualization
• D3.js
• Tableau
• Leaflet
• PowerBI
• ggplot2
• Shiny

7. Artificial Intelligence and Neural Networks
Any Idea

8. Involvement of AI in Data Science Prospects

9. Machine Learning Approach

10. Different Algorithms in Machine Learning

11. 11
Supervised vs. Unsupervised Learning
• Supervised learning
• Supervision: The training data (observations, measurements, etc.) are
accompanied by labels indicating the class of the observations
• New data is classified based on the training set
• Unsupervised learning
• The class labels of training data is unknown
• Given a set of measurements, observations, etc. with the aim of establishing the
existence of classes or clusters in the data

12. Regression is a technique used to model and analyze the relationships
between variables and often times how they contribute and are related to
producing a particular outcome together.
.
Machine Learning Depth : Regression Models

13. Linear Regression
• A classic statistical problem is to try to determine the relationship between a
random
variable Y. and an independent variable x.
• For example, we might consider height and weight of a sample of adults.
Linear regression attempts to explain this relationship by fitting a curve to the
data.
The linear regression model postulates that
Y= b0+b1 x1+ ... +bnxn+ e,where the xi are independent variables and the
"residual" e is a random variable with mean zero. In this applet, we consider the
simplest example of fitting a straight line:
Y= a+bx+e.The coefficients a and b are determined by the condition that the sum
of the square residuals is as small as possible

14. Linear Regression : Math Behind
• Using – the equation of a straight line y=mx+c
• Get the mean of all the x values
• Get the mean of all the y values and use the following equation (from C1)
• Plot the point this is the only point that we know on the line of regression.
• The only thing to do now is work out the gradient (m)
   
 
where (y-mx) is the intercept
y y m x x
y mx y mx
  
  
 
,
x y

15. Findthe gradient xy
xx
S
m
S

  
( )( )
xy i i
i i
i i
i i
S x x y y
x y
x y
n
x y nxy
  
 
 

 


 
2
2
2
2 2
( )
xx i
i
i
i
S x x
x
x
n
x nx
 
 
 




You need the different forms as
problems will be presented in
different ways.

16. In a graphics calculator
x y
= =
=Sxy
 
x x
  
y y
  
x x
  
y y

x
n

x
y
n

y
  
x x y y
 

=Sxx
x
2
( )
i
x x


 
x x
  
2
x x

i
x
n
x



17. Linear Regression : Math Behind

18. Nonlinear Regression
Given n data points )
,
(
,
...
),
,
(
),
,
( 2
2
1
1 n
n y
x
y
x
y
x best fit )
(x
f
y 
to the data, where )
(x
f is a nonlinear function of x
Figure. Nonlinear regression model for discrete y vs. x data
)
(x
f
y 
)
,
(
n
n
y
x
)
,
( 1
1
y
x
)
,
(
2
2
y
x
)
,
(
i
i
y
x
)
(
i
i
x
f
y 
http://numericalmethods.eng.usf.edu
18

19. Logistic Regression
• Logistic regression is the appropriate regression analysis to conduct
when the dependent variable is dichotomous (binary).
• Like all regression analyses, the logistic regression is a predictive
analysis.
• Logistic regression is used to describe data and to explain the
relationship between one dependent binary variable and one or more
nominal, ordinal, interval or ratio-level independent variables.

20. Logistic Growth Model
or (ignoring e) “rate of increase in Y =
 

 Y
kY
dx
dY 

Equation: e




 kx
e
Y
1
10
8
6
4
2
0
0.0
0.5
1.0
Logistic Growth Model
x
y

k=1/4
k=1/2
k=1
k=2
k=4

21. 21
Classification: Basic Concepts
• Classification: Basic Concepts
• Decision Tree Induction
• Bayes Classification Methods
• Rule-Based Classification
• Model Evaluation and Selection
• Techniques to Improve Classification Accuracy: Ensemble Methods
• Summary

22. 22
Decision Tree Induction: An Example
age?
overcast
student? credit rating?
<=30 >40
no yes yes
yes
31..40
fair
excellent
yes
no
age income student credit_rating buys_computer
<=30 high no fair no
<=30 high no excellent no
31…40 high no fair yes
>40 medium no fair yes
>40 low yes fair yes
>40 low yes excellent no
31…40 low yes excellent yes
<=30 medium no fair no
<=30 low yes fair yes
>40 medium yes fair yes
<=30 medium yes excellent yes
31…40 medium no excellent yes
31…40 high yes fair yes
>40 medium no excellent no
 Training data set: Buys_computer
 The data set follows an example of Quinlan’s ID3
(Playing Tennis)
 Resulting tree:

23. 23
Algorithm for Decision Tree Induction
• Basic algorithm (a greedy algorithm)
• Tree is constructed in a top-down recursive divide-and-conquer manner
• At start, all the training examples are at the root
• Attributes are categorical (if continuous-valued, they are discretized in advance)
• Examples are partitioned recursively based on selected attributes
• Test attributes are selected on the basis of a heuristic or statistical measure (e.g.,
information gain)
• Conditions for stopping partitioning
• All samples for a given node belong to the same class
• There are no remaining attributes for further partitioning – majority voting is employed
for classifying the leaf
• There are no samples left

24. Deep Learning Approach

25. Why Deep Learning in AI and Data Science?

26. Biological Inspiration
“My brain: It's my second favorite organ.”
- Woody Allen, from the movie Sleeper
Idea : To make the computer more robust, intelligent, and learn, …
Let’s model our computer software (and/or hardware) after the brain

27. Backbone of Deep Learning :- Neural Networks

28. Mathematics Behind Neural Networks
Biological Neuron
Artificial Neuron

29. Mathematical terminologies Deep Learning
Training Epochs :- An epoch is a single step in training a neural network; in other
words when a neural network is trained on every training samples only in one pass we
say that one epoch is finished.
Loss Functions :- It is used to measure the inconsistency between predicted value (^y )
and actual label (y ).
Learning Rate :- Learning rate is defined in the context of optimization, and
minimizing the loss function of aneural network.
Batch Size :- Batch size is a term used in machine learning and refers to the number of
training examples utilised in one iteration.
Optimizer :- Optimization Techniques are used in optimizing a Neural Network.
Activation Function :- Activation Function of a node defines the output of that node

30. Implementation :- Data Science and AI using Tensroflow
https://github.com/shubhamsharmacs/TensorFlow-Examples
Implement a Linear Regression with TensorFlow :-
https://tinyurl.com/ybxrwbwz
Implement a Logistic Regression with TensorFlow :-
https://tinyurl.com/y7esozs4
Implement Nearest Neighbor algorithm with TensorFlow:-
https://tinyurl.com/y8jecc6k
Build a Random Forest classifier with TensorFlow:-
https://tinyurl.com/y8uwf5bm
Build a simple neural network :-
https://tinyurl.com/y7ppk2tf
Build a convolutional neural network :-
https://tinyurl.com/yckjzjkf

31. Opportunities for Data Science and AI professionals
• Exponential growth in volume of
data being generated and handled
• Increasing awareness among
businesses about importance of
utilizing power of data
• Shortage of Data Scientist talent
supply globally: 200k to 500k as per
different sources

32. Q & A

33. Connect with me
• Gmail :- shubhamsharma1318@gmail.com
• Linkedln :- https://linkedin.com/in/shubham-sharma-8889893109/
• StackOverflow :-
https://stackoverflow.com/users/4786793/shubham-sharma
Blogs :- http://dataanalyticsvidhya.com/

34. •Thank You