UNITED COLLEGE OF ENGINEERING & RESEARCH
NAINI, PRAYAGRAJ (U.P.)-211010
Bachelor of Technology
In
Department of Computer Science & Engineering
A presentation on
MACHINE LEARNING
Name : Supriya Mishra
Roll-No. : 1801010159
Branch : Computer Science
TRAINING DETAILS
MACHINE LEARNING
Duration: 6 weeks
Date: 15th june-27th july,2020
From: Internshala
Mode: Online
HISTORY OF MACHINE LEARNING
In 1950, Alan Turing created the world-famous Turing Test to
determine “Can machine thinks like human?”.
In 1952, Arthur Samuel wrote the first computer learning
program .The program was the game of checkers.
In 1957, Frank Rosenblatt designed the first artificial neural
network called perceptron.
In 1979,students at Stanford University invent the "Stanford Cart"
which can navigate obstacles in a room on its own.
In 1985, Terry Sejnowski invented “NET talk” which
learns to pronounce words the same way as a baby does.
INTRODUCTION
Machine learning (ML) is the study in which " it gives computers the ability
to learn without being explicitly programmed ". - Arthur Samuel [1]
Machine learning is a part of larger domain ,which is artificial intelligence.
Machine learning is a field that makes prediction using algorithms. It helps
to make the machines learn from the data given to them.
The primary aim of machine learning is to develop method that can
automatically detect patterns in data ,and then by using that pattern predict
future data.
TYPES OF MACHINE LEARNING
Machine Learning
Supervised Unsupervised Reinforcement
Learning Learning Learning
Classification Regression Clustering Association
SOME TERMINOLOGY OF MACHINE LEARNING
Model : Model is the system which makes predictions
Feature :A feature is a measurable property or parameter of the data-set
Training :Algorithm takes a set of data known as “training data” as input
Prediction :Once the machine learning model is ready ,it can fed with input
data to provide predicted output
Target : The value that the machine learning model has to predict is called
target or label
SUPERVISED LEARNING
In this, we use labeled data or input data. The input data goes through the machine learning
algorithm and is used to train the model
Once the model is trained it can predict the future outputs
It required the help of previous data
Algorithm of Supervised Learning: Linear Regression, Decision Tree, Random Forest, KNN, Logistic
Regression etc.
Example: Identifying the picture of dog & cat
Fig: Image[2]
TYPES OF SUPERVISED LEARNING
CLASSIFICATION :
Ø It is a kind of learning where the output variable is a category, such as "red"
or "blue" and "disease" or "no disease"
Ø Application of classification are Email spam classification, Facial key point
detection, Biometric identification etc.
REGRESSION :
Ø It is a kind of learning where the output variable is a real or continuous value, , such
as "salary" or "weight"
Ø Application of regression are Market forecasting, Salary forecasting, Score prediction
Example: Predicting
Team Classification Win or lose
Team Regression Winning chance
UNSUPERVISED LEARNING
In unsupervised learning there is no labelled data. The input data goes through
the machine learning algorithm and is used to train the model
The trained model tries to search for pattern and give the output
Unsupervised learning needs no previous data as input
Algorithm of unsupervised learning are K-Means etc.
Example: Given an image of dog and cat identify it
Fig : Image[2]
TYPES OF UNSUPERVISED LEARNING
CLUSTERING :
Clustering allocates objects in such a ways that objects in the same group are more
similar to each other than to those in others group
Application of clustering in different fields are Marketing, Biology, Libraires,
Insurance
Example: Detecting skin disease
Association :
Association is a method for finding the relationship between variables in the large
databases
Application of association are Market basket analysis, Medical diagnosis, Protein
sequence
Example: If a customer buys bread, he is more likely of buying milk
REINFORCEMENT LEARNING
Three major components make up reinforcement learning:- The agent, the
environment, and the actions
In Reinforcement learning where an intelligent agent interact
with environment and learn to act within it
In this agent learns automatically using feedbacks without any labelled data
It is reward based algorithm
It used in self-driving car, robots training
APPLICATION OF MACHINE LEARNING
Machine learning is actively being used in our day-to-day life and its application is rapidly
increasing day by day. There is some popular application given in figure.
Fig - Application of machine learning[3]
WORKING OF MACHINE LEARNING
First we provide data to the system
The system goes through the entire data and analyzes it to find patterns based
on sizes, shapes, colors etc.
Now after figuring out patterns, the system takes decisions and starts
separating items
Once the work is done, the system learns from the result [3]
IMPORTANCE OF MACHINE LEARNING
They can detect anomalies and defects in the data
Ability to provide solution to complex problem
Helps in automating and create models for data analysis
It has wide applications in many areas
ADVANTAGE OF MACHINE LEARNING
Easy identifies trends and patterns
No Human Intervention Needed(Automation)
Continuous Improvement
Wide Applications
DISADVANTAGE OF MACHINE LEARNING
Data Acquisition
Time and Resources
Interpretation of Results
High Error Susceptibility
CONCLUSION
Iwould like to conclude machine learning has applications in
nearly every other field of study and is already being implemented
commercially because machine learning can solve problems which is
difficult or time consuming for humans to solve. Purpose of Machine
learning focuses on making predictions using computers and past
experience.
REFERENCES
[1]V. Advani, "What is Machine Learning? How Machine Learning Works and future
of it?", greatlearning blog. 2020 [Online]. Available:
https://www.mygreatlearning.com/blog/what-is-machine-learning/
[2]G. Vaseekaran, Machine Learning: Supervised Learning vs Unsupervised
Learning. 2018 [Online]. Available: https://medium.com/@gowthamy/machine-
learning-supervised-learning-vs-unsupervised-learning-f1658e12a780
[3]N. Jain, "Machine Learning-How it Works, Types, Applications, Advantages",
electricalfundablog.com. 2020 [Online]. Available:
https://electricalfundablog.com/machine-learning/. [Accessed: 10- Dec- 2020]
THANK YOU
Any Query?
