Introduction to Machine Learning
By,
Chetan
Contents
01 What is Machine Learning
02 Why M/L so important
03 How Does M/L Works?
04 Types of Machine Learning
05 Regression and Classification
06 Difference B/t Types of Machine Learning
07 Machine Learning Use Cases
Introduction to Machine Learning
Introduction and Definition of Machine Learning..
What is Machine Learning??
“Machine Learning is a application of Artificial Intelligence (AI)
that provides system, ability to automatically learn and improve
from its past experience without being explicitly programmed”
In Simple Words;
“If a computer can improves the certain task based on past
experience”
I.e., System predicts the value from an previous/past
experience
Machine Learning…
The ability of a computer to learn from data without
explicit programming. The machine learns from the
existing data and predicts future data.
Why Machine Learning is Important??
Importance of Machine Learning
Why Machine Learning is important???
How does Machine Learning impacting the industries
❖ Higher Accuracy of the Model
❖ Reduces the Human Efforts
❖ Greater/Higher efficiency
❖ Machine Learning process can help companies save time & money
How Does M/L Works??
Steps/Process involved in Machine Learning
How Does it Works??
Training Data
Train with ML
Algorithm
Successful Model
Model Input
Data Prediction
New Input
Data
Machine Learning Process
A machine learning project involves the following steps:
1. Defining a Problem
2. Data Gathering
3. Preparing Data (Data Cleaning)
4. Data Exploration
5. Build a M/L Algorithms
6. Evaluate/Validate the Model
7. Prediction
Types of Machine Learning
Introduction to Various types of Machine Learning
Types of Machine Learning
“Supervised Machine Learning is a learning we train or teach
the model or machine using labeled data.”
Supervised Learning
In Supervised Learning, a
model is able to predict
with the help of labeled
Dataset
Spoon
Known Data
Model Response
Known Response
New Data
“Unsupervised Machine Learning is a learning we train/teach
the model or machine using unlabeled data & allowing the
algorithm to act on that information without guidance.”
Unsupervised Learning
❑ An image of fruits is first fed into the system.
❑ The System identifies different fruits using pattern, characteristics like
color, size and categorizes them
❑ When a new fruit is shown, it analyses its features and put it into the
category having similar featured items
“Reinforcement Learning is works on “Principle of feedback”
In this process agent is put in an environment and
he learns to behave in this environment by performing certain
action based on trail and error.
Regression
ŷ i = b 0 + b1x
Regression analysis is used to:
❖ Predict the value of a dependent variable based on the value of at
least one independent variable
❖ Explain the impact of changes in an independent variable on the
dependent variable
❖ i.e., Changes in y are assumed to be caused by changes in x
Dependent variable: the variable who’s values need to be predicted
Independent variable: the variables used to predict the dependent variable
Classification
Classification is a method used to Predict a Dependent Variable(Y), Using given
set of Independent Variables(X)
• Dependent Variable is Categorical/Discrete in Nature
• Outcome also should be in Categorical/Discrete Value
Regression & Classification
Classification Regression
Supervised Vs. Unsupervised
Vs. Reinforcement
Difference between Various types of Machine Learning
Use Case of Machine Learning
Applications of Machine Learning
Weather Prediction
Helps to determine the kind of
weather that can be expected
Regression – Determines the Temp
/Continuous Data
Classification – Determines Sunny
(or) cloudy
Weather Prediction
Sentimental Analysis
“It is application of Natural Language
Processing (NLP) that builds systems
that try to identify and extract the
sentiment content or opinions behind
a series of word.”
Recommendation
System
Works on Similarity
Features
Image Categorization
Identifies the different items
that are present in the image,
and helps categorize them
Image Categorization
Other Applications of Machine Learning
Banking
+
Identification of loan risk applicants by their
probability of defaulting payments
Banking HealthCare Health Care
Identification of at risk patients and disease
Use- trends
Case
Marketing
Identification of Customer Churn
Remote Marketing
Sensing
Remote Sensing
Identification of areas of similar land use in a
GIS database
