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
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Data Science and Machine Learning with Tensorflow
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
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
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
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
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
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