Download CS 434 Machine Learning and Data Mining

CS 434 Machine Learning and Data Mining
Description:
Introduction to machine learning and data mining algorithms and tools
that are widely employed in industrial and research settings. Topics
include: 1) Supervised learning for prediction problems, both discrete
and real-valued, 2) Unsupervised learning for clustering data and
discovering patterns in data sets, 3) Reinforcement learning for
learning to control complex processes based on positive and negative
feedback. The course will have a practical focus and will require
applying machine learning and data mining techniques to real problems
on programming assignments and written homework assignments.
Credits:
4
Meeting hours per week:
3 lecture hours per week
Prerequisites:
CS325 (enforced)
Syllabus:
Supervised learning:
linear regression,
linear classifiers,
decision trees,
ensemble methods,
evaluation of supervised learning
Unsupervised learning:
agglomerative clustering,
k-means clustering,
dimensionality reduction and visualization,
frequent pattern mining using the Apriori algorithm
Reinforcement learning:
Markov decision processes
Q-learning
Function approximation (if time allows)
Policy search (if time allows)
Learning Objectives:
Upon completing the course, students will be able to:
1) Apply supervised learning algorithms to prediction problems and evaluate the results.
2) Analyze data using unsupervised learning programs and evaluate the performance..
3) Implement and test reinforcement learning for control and optimization problems.
4) Formulate given learning problems appropriately as instances of supervised,
unsupervised, or reinforcement learning problem.
Grading Policy:



Assignments (Written and Programming) - 40%
Midterm - 20%
Final Exam - 40%
Learning Resources:
Machine Learning, Tom Mitchell, McGraw Hill, 1997
Students with Disabilities:
Accommodations are collaborative efforts between students, faculty and Services for
Students with Disabilities (SSD). Students with accommodations approved through SSD
are responsible for contacting the faculty member in charge of the course prior to or
during the first week of the term to discuss accommodations. Students who believe they
are eligible for accommodations but who have not yet obtained approval through SSD
should contact SSD immediately at 737-4098.
Link to Statement of Expectations for Student Conduct, i.e., cheating policies
http://oregonstate.edu/admin/stucon/achon.htm