Machine Learning Damon Waring 22 April 2003... Machine Learning “The study of computer algorithms that improve automatically through experience” –Tom Mitchell, Machine Learning
Trang 1Machine Learning
Damon Waring
22 April 2003
Trang 2 Problem, Solution, Benefits
Machine Learning Overview/Basics
Face detection, recognition, and
demo
How this applies to us
Summary
Trang 3Software frequently requires users
or developers to do simple,
repetitive tasks
Trang 4 Machine Learning
“The study of computer algorithms
that improve automatically through
experience” –Tom Mitchell, Machine
Learning
Machine learning uses include:
Security (Pattern recognition, face
recognition)
Business (Stocks, user behaviors)
Medical (Research)
Ease of Use (Focus of this presentation)
Algorithms that execute based on experience
Algorithms that execute based on experience
Trang 5 Makes human-computer interaction
easier
Relatively simple to integrate
Will distinguish your product from
others
Increase customer satisfaction
Will improve simple intelligent systems (ex: Microsoft Word’s grammar
checker)
Enhances the user experience
Enhances the user experience
Trang 6High Level Operation:
Recognition Algorithms
Training Set
Iteratively analyze
inputs and refine
algorithm
Store learned data
Operation Mode Operation Mode
New input
Process input using learned data
Produce a decision
Recognition algorithms are taught and react like humans
Recognition algorithms are taught and react like humans
“Learn from nature It has had 4 billion years
to develop its techniques” – My Dad
Trang 7Case Study: Artificial
Neural Network
Neural Network
weight each input
has on final decision
if the decision is
true, 0 if it is false
make up an artificial
neural network
Group of weighted input values determine a binary output
Group of weighted input values determine a binary output
Trang 8Face Detection
1 Image pyramid used to locate faces of different sizes
2 Image lighting compensation
3 Neural Network detects rotation of face candidate
4 Final face candidate de-rotated ready for detection
Trang 9Face Detection (Con’t)
mouth, etc)
Trang 10Face Recognition and
demo
Demo: Hidden Markov Model Face
Recognition
respect to each other
“fingerprint” created by distances
between features
Demo is from OpenCV – Intel’s open source computer vision library
Implementations vary widely and have different success rates
Implementations vary widely and have different success rates
Trang 11Adobe Photoshop Album
Software that organizes digital
pictures
Tags are dragged to each photo to
categorize it
Tagging 100’s of photos is tedious
Face recognition could automatically tag photos or replace tags altogether
Machine learning can be used to make everyday apps easier
Machine learning can be used to make everyday apps easier
Trang 12Current Uses of ML
accesses
Recognition to digitize newspapers
Deep Blue, but smarter because of
Neural Networks
Trang 13Other Areas
Trang 14 Machine learning is possible today
Large amounts of research are available
Quality open source code available in
some areas
Will require time and creativity to
implement
Why do it? Makes human-computer
interface simpler
Trang 15http://sourceforge.net/projects/opencvlibrary/
Understanding,” “Artificial Intelligence,” “Neural Networks”
“Image Processing”
embedded HMM for face detection and recognition.” Nefian, A.V.; Hayes, M.H III; Image Processing, 2000 Proceedings 2000 International Conference on, Volume: 1, Pages 33-36
Analysis and Machine Intelligence, IEEE Transactions on, Volume 20 Issue 1, Jan
1998 Pages 23-38 (Paper posted at: http://www.ri.cmu.edu/projects/project_271.html )
http://www.ri.cmu.edu/projects/project_271.html