The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Many successful applications of machine learning exist already, including systems that analyze past sales data to predict customer behavior, optimize robot behavior so that a task can be completed using minimum resources, and extract knowledge from bioinformatics data
3. The goal of machine learning is to program
computers to use example data or past experience to
solve a given problem. Many successful applications
of machine learning exist already, including systems
that analyze past sales data to predict customer
behavior, optimize robot behavior so that a task can
be completed using minimum resources, and extract
knowledge from bioinformatics data
4. A branch of artificial intelligence, concerned with the
design and development of algorithms that provides the
ability to computers to learn without being explicitly
programmed
As intelligence requires knowledge, it is necessary for the
computers to acquire knowledge
6. 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
8. Supervised learning --- where the algorithm
generates a function that maps inputs to desired
outputs.
One standard formulation of the supervised
learning task is :-
classification problem: the learner is required to
learn (to approximate the behavior of) a function
which maps a vector into one of several classes by
looking at several input-output examples of the
function.
9. Unsupervised learning --- which models a set of
inputs: labeled examples are not available
Learning “what normally happens”
No output
Clustering: Grouping similar instances
Example applications
Customer segmentation in CRM
Image compression: Color quantization
Bioinformatics: Learning motifs
10. where the algorithm learns a policy of how to act
given an observation of the world. Every action has
some impact in the environment, and the
environment provides feedback that guides the
learning algorithm
Applications:
Game playing
Robot in a maze
Multiple agents, partial observability, ...
11. ➨It is used by google and facebook to push relevant
advertisements based on users past search behaviour.
➨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.
12. ➨Interpretation of results is also a major challenge to
determine effectiveness of machine learning algorithms.
➨Based on which action to be taken and when to be taken,
various machine learning techniques are need to be try.
13. Face detection
Object detection and recognition
Image segmentation
Multimedia event detection
Economical and commercial usage
14. 1) People-Literate Technology or PLTs: They can covert
voice or text messages into retainable intelligence will
dominate personal communication and by 2020, about
40 percent people will use PLTs as the primarily mode
of technological interaction.
2) The Brain-Computer Interface: Claims to provide
certain brain patterns to the computer for controlling a
device or a program will also become popular.
3) Bioacoustics: These technologies are front-runners in
the world of digital humanism that connects humans
with digital businesses and workplaces. Apart from
connected homes, smart robots, and self-driving cars,
bioacoustics may also become important.
15. • Machine Learning is for everyone!
• Relatively simple algorithms lying around for use
• Can help researcher understand their data initially
• Can help drill-down into sub-populations
• Can automate monotonous labeling tasks
• Available in
– Python (Scikit-learn, Orange, Weka)
– Matlab (Statistics, Neural Net, Fuzzy Logic Toolboxes)
– Most languages (OpenCV)
16. Journal of Machine Learning Research www.jmlr.org
Machine Learning
IEEE Transactions on Neural Networks
IEEE Transactions on Pattern Analysis and Machine
Intelligence
Annals of Statistics
Journal of the American Statistical Association
...