INTERNATIONAL CENTRE OF EXCELLENCE
IN ENGINEERING AND MANAGEMENT
COMPCOMPUTER SCIENCE AND ENGINEERING
ROF.B.G.
COMPUTER SCIENCE AND ENGINEERING
UCOMPUTER SCIENCE AND ENGINEERING
COMPUTER SCIENCE AND ENGINEERING
TECOMPTER SCIENCE AND ENGINEERING
SEMINAR ON
R SCIENCE AND ENGINEERING
MACHINE LEARNING
GUIDED BY : [Link]. PRESENTED BY : ERANDE RANI.
machine learning
Contents :
Introduction
Importance
Types of machine learning
Characteristics
Technology
Tools
Applications
Advantages
Future
Conclusion
Introduction :
What is machine learning :
Machine Learning is the computerized approach to analyzing computational
work that is based on both a set of theories and a set of technologies.
Machine Learning is a sub-field of Artificial Intelligence which concerns with
developing computational theories of learning and building learning
machines.
The goal of machine learning :
to achieve a thorough understanding about the nature of learning process
(both human learning and other forms of learning), about the computational
aspects of learning behaviors, and to implant the learning capability in
computer systems.
Machine learning has been recognized as central to the success of Artificial
Intelligence, and it has applications in various areas of science, engineering
and society.
The goal Machine Learning :
The field of machine learning can be organized around three primary research Areas :
Task-Oriented Studies : The development and analysis of learning systems
oriented toward solving a predetermined set, of tasks .
Cognitive Simulation : The investigation and computer simulation of human
learning processes .
Theoretical Analysis : The theoretical exploration of the space of possible learning
methods and algorithms independent application domain .
Growth of Machine Learning :
Machine learning is preferred approach to
Speech recognition, Natural language processing
Computer vision
Medical outcomes analysis
Robot control
Computational biology
This trend is accelerating
Improved machine learning algorithms
Improved data capture, networking, faster computers
Software too complex to write by hand
New sensors / IO devices
Demand for self-customization to user, environment
Types of Learning :
1. Supervised learning :
• In supervised learning, the computer is
provided with example inputs that are
labeled with their desired outputs.
• It uses patterns to predict label values on
additional unlabeled data.
• Example : facial recognition
2. Unsupervised learning :
• Training data does not include desired
outputs
• It is opposite to supervised learing
• Example : clustering
3. Semi-supervised learning
• Semi-supervised learning is .used for the same application as supervised
learning . but it uses both labeled and unlabeled data for training .
• It can be used with methods such as classification , regression and prediction
• Example : identifying a persons face on web cam.
4. Reinforcement learning
• It is used for robotics ,gaming and navigation.
• It has three component : 1. agent
2. environment
3. action
Characteristics of machine learning :
The ability to perform automated data visualization .
automation at its best Automation at its best
The ability to take efficiency to the next level when merged with IoT
Accurate data analysis
Business intelligence at its best
Robust ,reliable , scalable and efficient
Tools of Machine Learning :
AMAZON WEB SERVICES
AI-ONE
DEEPLEARNING4J
APACHE MAHOUT
PYTORCH
WEKA
KNIME
SHOGUN
Applications of machine learning :
Web search
Computational biology
Finance
E-commerce
Space exploration
Robotics
Information extraction
Social networks
Debugging
[Your favorite area]
Advantages of Machine Learning :
Useful where large scale data is available .
It has capabilities to handle multi-dimensional and multi-variety data in dynamic or
uncertain environments.
It allows time cycle reduction and efficient utilization of resources.
Due to machine learning there are tools available to provide continuous quality
improvement in large and complex process environments.
Source programs such as Rapidminer helps in increased usability of algorithms for
various applications.
The Future of Machine Learning :
Lots of areas of impact:
Learn across multiple data bases, as well as web and news feeds
Learn across multi-media data
Cumulative, lifelong learning
Agents with learning embedded
Programming languages with learning embedded?
Learning by active experimentation systems
Conclusion :
Machine learning is an extraordinary achievement in the field of artificial intelligence. while it
has some starting ramifications when you consider it ,these machine learning applications are a
few of numerous way this innovation can enhance our lives. With the advancement in
technologies and innovations and with the digitalization what necessary is not only to come
with new and more efficient algorithms but to study the performance of present algorithms to
obtain more productive outcomes .
THANK YOU