Machine Learning

Intetics Inc.
10001 Tamiami Tr N, Suite 114
Naples, Florida 34108
United States
www.intetics.com
intetics@intetics.com
Office: +1-239-217-4907
MACHINE LEARNING

Intetics Inc. | 10001 Tamiami Tr N, Suite 114, Naples, Florida 34108, United States
Office: +1-239-217-4907 | intetics@intetics.com | www.intetics.com
“A breakthrough in machine learning
would be worth ten Microsofts.”
— Bill Gates, Former Chairman, Microsoft

Machine Learning is the science of
getting computers to learn and act
like humans do, and improve their
learning over time in autonomous
fashion, by feeding them data and
information in the form of
observations and real-world
interactions.
What is Machine Learning?

Call it AI if that helps you sell it, but know
that AI is a buzzword that can mean
whatever people want it to mean. Machine learning means
learning from data;
AI is a buzzword. Machine learning lives
up to the hype: there are an incredible
number of problems that you can solve
by providing the right training data to
the right learning algorithms.
Fact Box
What is Machine Learning?

Traditional Programming vs Machine Learning
Traditional Programming: Data and
program is run on the computer to
produce the output.
Machine Learning: Data and output is
run on the computer to create a
program. This program can be used in
traditional programming.

How is machine learning used?
Web search
Computational biology
Finance
E-commerce
Space exploration
Robotics
Information extraction
Social networks
Debugging
Machine Learning enables organisations to
analyse complex data automatically at scale
and with tremendous accuracy.
It gives organisations the insight they need to
make data-driven decisions about their
operations.

Key Elements of Machine Learning
the way to represent knowledge
Representation
the way to evaluate candidate programs
(hypotheses)
Evaluation
the way candidate programs are generated
known as the search process
Optimization

Examples:
o Decision trees
o Sets of rules / Logic programs
o Instances
o Graphical models (Bayes/Markov nets)
o Neural networks
o Support vector machines
o Model ensembles
Representation
the way to represent knowledge

Examples:
o Accuracy
o Precision and recall
o Squared error
o Likelihood
o Posterior probability
o Cost / Utility
o Margin
o Entropy
o K-L divergence
Evaluation
the way to evaluate candidate programs (hypotheses)

Examples:
o Greedy search
o Gradient descent
o Linear programming
Optimization
the way candidate programs are generated known
as the search process
Combinatorial
optimization
Convex optimization
Constrained optimization
Types:

Types of Learning
Supervised (inductive) learning
• Training data includes desired outputs
Unsupervised learning
• Training data does not include desired outputs
Reinforcement learning
• Rewards from sequence of actions

o Human expertise does not exist
(navigating on Mars)
o Humans are unable to explain their
expertise (speech recognition)
o Solution changes in time (routing on a
computer network)
o Solution needs to be adapted to
particular cases (user biometrics)
Machine Learning is useful when:

“Humans can typically create one or
two good models a week; machine
learning can create thousands of
models a week.”
— Thomas H. Davenport, Analytics thought
leader
excerpt from The Wall Street Journal

o Yelp – Image Curation at Scale
Yelp’s machine learning algorithms help the
company’s human staff to compile, categorize, and
label images more efficiently.
o Pinterest – Improved Content Discovery
Machine Learning touches virtually every aspect
of Pinterest’s business operations, from spam
moderation and content discovery to advertising
monetization and reducing churn of email
newsletter subscribers.
Some companies using Machine Learning in cool ways

Some companies using Machine Learning in cool ways
Netflix saved $1 billion this
year recommending
personalized TV show and
movies to subscribers.
Fact Box
o Netflix – uses algorithms to keep its viewers
engaged and reduce cancellations
When you think of leaders in Machine Learning
(ML), Netflix doesn't usually jump to the top of
the list. But facts say some of its ML algorithms
save Netflix $1 billion each year.

Machine Learning challenges
“A baby learns to crawl, walk and then
run. We are in the crawling stage when it
comes to applying machine learning.”
- Dave Waters, Associate Professor at
University of Oxford

What’s subsequent in
machine studying traits?
o Machine that learn more effectively
o Automation of cyberattack countermeasures
o Convincing generative models
o Better machine learning training
The future of Machine Learning

o Most applications will include
machine learning
o Machine learning as a service
will become more common
o Computers will get really good
at talking like humans
o Algorithms will constantly retrain
o Specialized hardware will deliver
performance breakthroughs
The future of Machine Learning

Machine Learning

More Related Content

Similar to Machine Learning (20)

More from Intetics (20)

Recently uploaded (20)

Machine Learning