Scribd
Upload
34 views

Note 1

The document provides an introduction to machine learning, covering its history from early programs that played games like checkers in the 1950s to modern applications. It discusses different types of learning including supervised, unsupervised, reinforcement, and semi-supervised learning. Examples of machine learning applications mentioned include traffic alerts, social media, transportation, product recommendations, virtual assistants, self-driving cars, dynamic pricing, and Google Translate.

Uploaded by

Brijesh Kundu
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
34 views

Note 1

The document provides an introduction to machine learning, covering its history from early programs that played games like checkers in the 1950s to modern applications. It discusses different types of learning including supervised, unsupervised, reinforcement, and semi-supervised learning. Examples of machine learning applications mentioned include traffic alerts, social media, transportation, product recommendations, virtual assistants, self-driving cars, dynamic pricing, and Google Translate.

Uploaded by

Brijesh Kundu
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

Introduction to Machine

Learning
Debmani Saha
Assistant Professor
NSHM Knowledge Campus Durgapur
Contents
● Introduction to Machine Learning
● Feature Engineering
● Learning Paradigm
● Generalization of Hypothesis
● VC Dimension
● PAC Learning
● Applications of ML
What is Machine Learning?
Machine learning (ML) is
a type of artificial
intelligence (AI) that
allows software
applications to become
more accurate at
predicting outcomes
without being explicitly
programmed to do so.
History of Machine Learning
Arthur Samuel of IBM developed a computer program for playing
checkers in the 1950s. Since the program had a very small amount Game
of computer memory available, Samuel initiated what is called
alpha-beta pruning. His design included a scoring function using of
the positions of the pieces on the board. The scoring function
attempted to measure the chances of each side winning. The Checkers
program chooses its next move using a minimax strategy, which
eventually evolved into the minimax algorithm.
Samuel also designed a number of mechanisms allowing his
program to become better. In what Samuel called rote learning, his
program recorded/remembered all positions it had already seen
and combined this with the values of the reward function. Arthur
Samuel first came up with the phrase “machine learning” in 1952.
History of Machine Learning(contd….)

● In 1957, Frank Rosenblatt – at the Cornell Aeronautical Laboratory – combined


Donald Hebb’s model of brain cell interaction with Arthur Samuel’s machine
learning efforts and created the perceptron.
● In the 1960s, the discovery and use of multilayers opened a new path in neural
network research.
● In 1967, the nearest neighbor algorithm was conceived, which was the beginning of
basic pattern recognition. This algorithm was used for mapping routes and was one
of the earliest algorithms used in finding a solution to the traveling salesman
problem of finding the most efficient route.
History of Machine Learning(contd….)
● Backpropagation, developed in the 1970s, allows a network to adjust its hidden
layers of neurons/nodes to adapt to new situations.
● In 1980, advanced decision tree and rule learning developed.
● 1990 onwards, concepts were grown about Support Vector Machine, data mining,
text learning, ensemble, bayesian network etc.
● 2009 google developed self driving car.
Learning
It is the ability to improve behaviour based on experiments.
Features

1. Choose the training experience.

2. Choose the target function(that is to be learned).


Class of Functions
3. Choose how to represent the target function.

4. Choose a learning algorithm to infer the target function.


Different Types of Learning

Supervised Learning Unsupervised Learning Reinforcement Learning

Semi- supervised
Learning
Supervised Learning
New Input X

X Y

Learning
Input 1 Output 1
Algorithm Model
Input 2 Output 2

Input 3 Output 1
. .
. .
. . Output Y
Input n Output n
Unsupervised Learning
Reinforcement Learning
Semi supervised Learning
Applications of Machine Learning

● Traffic Alerts.
● Social Media.
● Transportation and Commuting.
● Products Recommendations.
● Virtual Personal Assistants.
● Self Driving Cars.
● Dynamic Pricing.
● Google Translate.

You might also like