HINDUSTHAN Educate Empower Excel

College of Engineering and Technology

Machine Learning
Handled by
Mrs.R.Gayathri
AP/CSE/HICET
MACHINE LEARNING 1
 CONTENTS

 Introduction to Machine Learning

 Definition of Machine Learning
 Comparison of AI,ML,DL
 Why it is Called Machine Learning ?
 Examples
 Applications of Machine Learning
 Classification of Machine Learning
 Supervised Learning
 Unsupervised Learning
 Reinforcement Learning

Educate Empower Excel

MACHINE LEARNING 2
Introduction to Machine Learning
 Machine learning is programming computers to optimize a
performance criterion using example data or past experience.

 We have a model defined up to some parameters, and learning

is the execution of a computer program to optimize the
parameters of the model using the training data or past
experience.

 The model may be predictive to make predictions in the

future, or descriptive to gain knowledge from data, or both.

Educate Empower Excel MACHINE LEARNING 3

 Definition of Machine Learning
 Machine learning is a subfield of artificial intelligence, which
is broadly defined as the capability of a machine to imitate
intelligent human behavior.
 Artificial intelligence systems are used to perform complex
tasks in a way that is similar to how humans solve problems.
 Machine learning is a modern innovation that has enhanced
many industrial and professional processes as well as our
daily lives.
 It's a subset of artificial intelligence (AI), which focuses on
using statistical techniques to build intelligent computer
systems to learn from available databases

Educate Empower Excel MACHINE LEARNING

HICET 4
 Comparison of AI,ML,DL

Educate Empower Excel MACHINE LEARNING

HICET 5
 Comparison of AI,ML,DL

Educate Empower Excel MACHINE LEARNING

HICET 6
 Why it is Called Machine Learning ?
 The term “machine learning” was coined by Arthur
Samuel, a computer scientist at IBM and a pioneer in
AI and computer gaming.
 Samuel designed a computer program for playing
checkers.
 The more the program played, the more it learned
from experience, using algorithms to make
predictions

Educate Empower Excel

HICET MACHINE LEARNING 7
 Examples
Handwriting recognition learning problem
 Task T: Recognising and classifying handwritten
words within images
 Performance P: Percent of words correctly classified
 Training Experience E: A dataset of handwritten
words with given classifications

Educate Empower Excel

HICET MACHINE LEARNING 8
 Examples
A robot driving learning problem
 Task T: Driving on highways using vision sensors
 Performance Measure P: Average distance traveled
before an error
 Training Experience: A sequence of images and
steering commands recorded while observing a human
driver

Educate Empower Excel

HICET SOFTWARE ARCHITECTURE 9
 Examples
iii) A chess learning problem
 Task T: Playing chess
 Performance Measure P: Percent of games won
against opponents
 Training Experience E: Playing practice games
against itself

Educate Empower Excel

HICET MACHINE LEARNING 10
 Applications of Machine Learning

Educate Empower Excel

HICET MACHINE LEARNING 11
 Classification of Machine
Learning
At a broad level, machine learning can be classified
into three types:
 1. Supervised learning
 2. Unsupervised learning
 3. Reinforcement learning

Educate Empower Excel

HICET MACHINE LEARNING 12
 Supervised Learning
 Supervised learning is a type of machine learning method in
which we provide sample labeled data to the machine
learning system in order to train it, and on that basis, it
predicts the output.
 The system creates a model using labeled data to understand
the datasets and learn about each data, once the training and
processing are done then we test the model by providing a
sample data to check whether it is predicting the exact output
or not.
 Supervised learning can be grouped further in two categories
of algorithms:
 Classification
 Regression

Educate Empower Excel

HICET MACHINE LEARNING 13
 Supervised Learning

Educate Empower Excel MACHINE LEARNING 14

HICET
 Unsupervised Learning

Unsupervised learning is a learning method in which a

machine learns without any supervision.
In unsupervised learning, we don't have a
predetermined result. The machine tries to find useful
insights from the huge amount of data. It can be
further classifieds into two categories of algorithms:
o Clustering
o Association

Educate Empower Excel

HICET MACHINE LEARNING 15
 Unsupervised Learning

Educate Empower Excel

HICET MACHINE LEARNING 16
 Reinforcement Learning

 Reinforcement learning is a feedback-based learning

method, in which a learning agent gets a reward for
each right action and gets a penalty for each wrong
action.
 The agent learns automatically with these feedbacks
and improves its performance.
 In reinforcement learning, the agent interacts with the
environment and explores it.
 The goal of an agent is to get the most reward points,
and hence, it improves its performance.
Educate Empower Excel
HICET MACHINE LEARNING 17
MACHINE LEARNING 18
 Thank you

Educate Empower Excel 19

MACHINE LEARNING