Professional
Practices
Presented To
Sir Ikram Ul Haq
Presented By
Tayyab Nawaz
17581556-003
BS-IT-17-A

Machine
Learning

TABLE OF
CONTENT
1. Definition
2. What is machine learning
3. Traditional programming and machine learning
4. Why machine learning is important
5. Generalization
6. Algorithms
7. Other learning techniques
8. Examples
9. Applications
10. Few quotes
11. Question and answers

Introduction
A branch of artificial
intelligence, concerns
the construction and
study of systems that
can learn from data.

Definition
In 1959, Arthur Samuel defined machine learning as a "Field of study that
gives computers the ability to learn without being explicitly programmed".
“The goal of machine learning is to build computer systems that can adapt
and learn from their experience.” Tom Dietterich.
Tom M. Mitchell provided a widely quoted, more formal definition: "A
computer program is said to learn from experience E with respect to some
class of tasks T and performance measure P, if its performance at tasks in T,
as measured by P, improves with experience E"

So, What Is
Machine
Learning?
Automating automation
Getting computers to program
themselves
Writing software is the bottleneck
Let the data do the work instead!

Why
Machine
Learning is
Important
Some tasks cannot be defined well,
except by examples (e.g., recognizing
people).
Relationships and correlations can be
hidden within large amounts of data.
Machine Learning/Data Mining may be
able to find these relationships.
Human designers often produce
machines that do not work as well as
desired in the environments in which they
are used.

Generalization
A core objective of a learner is
to generalize from its
experience.
Generalization in this context is
the ability of a learning
machine to perform accurately
on new, unseen examples/tasks
after having experienced a
learning data set.

Algorithm types
Machine learning algorithms can be organized
based on the desired outcome of the algorithm
or the type of input available during training the
machine
1. Supervised learning algorithms are trained
on labeled examples, i.e., input where the
desired output is known.
2. Unsupervised learning algorithms operate
on unlabeled examples, i.e., input where the
desired output is unknown.

Algorithm types
3. Semi-supervised learning combines both labeled
and unlabeled examples to generate an
appropriate function or classifier.
4. Reinforcement learning is concerned with how
intelligent agents ought to act in an environment
to maximize some notion of reward from sequence
of actions
Other algorithms are:
 Learning to learn
 Developmental learning
 Transduction etc.

Other
Learning
Techniques
Artificial neural networks
Inductive logic programming
Support vector machines
Bayesian networks
Reinforcement learning
Association Rule learning
Clustering

Applications of
Machine
Learning
Object recognition
Natural language
processing
Search engines
Brain-machine interfaces
Stock market analysis
Classifying DNA
sequences
Speech and handwriting
recognition
Software engineering
Adaptive websites
Robot locomotion
Computational advertising
Computational finance
Recommender systems

Software
suites
containing
a variety of
machine
learning
algorithms
Ayasdi
Apache Mahout
Gesture Recognition Toolkit
IBM SPSS Modeler
MATLAB, mlpy
Oracle Data Mining
Orange
Python scikit-learn
SAS Enterprise Miner
 STATISTICA Data Miner, and Weka

A Few Quotes
 “A breakthrough in machine learning would be
worth ten Microsoft's” (Bill Gates, Chairman,
Microsoft)
 “Machine learning is the next Internet” (Tony
Tether, Director, DARPA)
 Machine learning is the hot new thing” (John
Hennessy, President, Stanford)
 “Web rankings today are mostly a matter of
machine learning” (Prabhakar Raghavan, Dir.
Research, Yahoo)
 “Machine learning is today’s discontinuity” (Jerry
Yang, CEO, Yahoo)

Conclusion
Machines should be able to do all the things
what we can do & machine learning will play
a big role in achieving this goal.
References:-
1. Wikipedia
2. Machine learning summary - Greg Grudic
CSCI-4830
3. CSE 546 Data Mining Machine Learning
4. SlideShare