CS570 - Machine Learning
Course Information
-
Course title: CS570 - Topics in AI: Machine Learning
-
Course description: One of the many definitions of Machine
Learning (ML) is "Any change in a system that allows it to perform better
the second time on repetition of the same task or on another task
drawn from the same population" (Simon, 1983). Practically this means developing
computer programs that automatically improve their performance through
experience. The course covers the basic concepts and techniques of Machine
Learning from both theoretical and practical perspective. The material
includes classical ML approaches as Version Spaces, Decision Trees and
Bayesian Learning as well as new approaches as Relational Learning and
Minimum Description Length Principle (MDL). All topics are accompanied
with hands-on exercises with implementations of ML algorithms.
-
Course dates: June 1 - July 22, 2010
-
Location: Online
Course Goals
-
To introduce students to the basic concepts and techniques of Machine Learning.
-
To develop skills of using recent machine learning software for solving
practical problems.
-
To gain experience of doing independent study and research.
Course Topics
-
Introduction: machine learning problems, types of learning, designing a
learning system
-
Inductive learning: introducing basic concepts by example (learning semantic
networks), general setting for induction
-
Languages for learning: propositional (attribute-value), relational, Prolog
-
Hypothesis space: version space learning
-
Divide and conquer approaches: induction of decision trees, OneR, ID3
-
Covering strategies: least general generalization approaches
-
Searching the generalization/specialization graph
-
Relational Learning and Inductive Logic Programming
-
Evaluating hypotheses: error-based and MDL evaluation
-
Bayesian learning
-
Bayesian belief networks
-
Instance-based learning
-
Analytical (Explanation-Based) Learning
-
Unsupervised learning: clustering
Required Textbook
Machine Learning, Tom Mitchell, McGraw , 1997, 0-07-042807-7
Required Software
SWI-Prolog (http://www.swi-prolog.org/)
- free Prolog compiler, licensed under the GNU Public License. Portable
to many platforms, including almost all Unix/Linux platforms, Windows,
MacOS X and many more. More information about using SWI-Prolog for this
course will be provided in the course content modules.
Grading Policies
Grading will be based on five assignments and class participation through
threaded discussions. The letter grade will be determined by the following
grading scale:
A |
A- |
B+ |
B |
B- |
C+ |
C |
C- |
D+ |
D |
D- |
F |
950-1000 |
900-949 |
870-899 |
840-869 |
800-839 |
770-799 |
740-769 |
700-739 |
670-699 |
640-669 |
600-639 |
0-599 |
Late assignments will be marked one letter grade down for each 3 days
they are late. It is expected that all students will conduct themselves
in an honest manner and NEVER claim work which is not their own. Violating
this policy will result in a substantial grade penalty or a final grade
of F.
General Web Resources
Instructor Information
-
Name: Zdravko Markov, Ph.D
-
Email: markovz@ccsu.edu
-
URL: http://www.cs.ccsu.edu/~markov/
-
Phone: (860) 832-2711
-
Biography: Dr. Zdravko Markov has an M.S. in Mathematics and
Computer Science and a Ph.D. in Artificial Intelligence. He has been teaching
and doing research in the area of Machine Learning for more than 15 years.
Recently he developed a novel approach to conceptual clustering and is
studying its application to Data Mining tasks. Dr. Markov has published
4 textbooks and more than 50 research papers in conference proceedings
and journals. His most recent book (co-authored with Daniel Larose) is
“Data Mining The Web: Uncovering Patterns in Web Content, Structure, and
Usage", published by Wiley in 2007. Dr. Markov’s CCSU courses are in the
areas of Computer Architecture and Design, Computing and Communication
technology, Machine Learning, Data and Web Mining.