CSE 515A - Fall 2005 - Intelligent Data Analysis

---

Text book:
    R.E. Neapolitan, Learning Bayesian Networks, Prentice Hall, 2003, ISBN: 0130125342
Reference book:
    C. Borgelt and R. Kruse, Graphical Models: Methods for Data Analysis and Mining, John Wiley & Sons, 2002, ISBN: 0470843373

Newsgroup: tba (course related announcement and discussions will be posted there)

Instructor office hours: Friday 3-4pm, Jolley Hall 506, or by appointment

Because we will cover many topics that are not in the textbook nor the reference book, it is critical to attend every lecture. 

Brief description (in course listings)
Lecture and topic schedule
Additional information (project and final grade)
Collaboration policy

Brief description:

We very often cry for knowledge while immersed with huge amount of data.  Finding models intrinsic to the production of data we collect and patterns characteristic to the nature of observations we make is of fundamental and practical importance.  In this course, we study various advanced techniques (e.g., graphical models and spectral graph theory) from computer science, artificial intelligence and statistics for analyzing large quantity of data.  We consider applications in selected domains, such as computational biology and text mining on the web. 

Note: 1) In this semester, we will consider problems in genomics and biology. 2) This course can be considered as a continuation and extension of CSE 514A Datamining.  It will be very helpful if you have taken that course first, although that is not a prerequisite.

Lecture and topic schedule (Note: this is just an outline; details to be added later.)

******** Uncertainty and independency ********

• Basic concepts: uncertainty, independency, causal relationship; probability distribution, bayes method; some basic biology concepts
  
• Number of lectures: ~4
  

******** Graphical models of Uncertainty and independency ********

• Basic concepts: Markov networks and Bayesian networks
  
• Number of lectures: ~5
  

******** Learning graphical models ********

• Basic concepts: Learning Markov and Bayesian networks
• Applications and Projects: Learning and building network representation from biological data
  
• Number of lectures: ~10

******** Feature extraction, feature selections and model building ********

• Basic concepts: curse of dimentionality, dimention reduction using principle component analysis, singular value decomposition and other methods; other feature extraction and selection methods; building discriminative models
• Applications: microarray feature selection; finding regulatory motif modules
  
• Number of lectures: ~5

******** Time series analysis ********

• Basic concepts: time course data; basic methods
• Applications: time series microarray data analysis and finding cell cycle related genes
  
• Number of lectures: ~4

Information on project and grading

• Homework Assignments: There will be small sets of homework problems.  They are designed to help you understand the basic concepts and methods.  However, the problems will not be graded rigurously and will only carry 15% of the total grade.  The assignments are due either in the instructor's office in Jolley 506 before the class or in class at the beginning of the class of a given due date. Any homework submitted in class after 1:30pm will be given a 15 point late penalty. If you arrive to class after 1:30, wait until the end of class to bring up your homework. It is VERY disruptive to have students walking in late and coming to the front of the class to submit their homeworks. No assignments will be accepted after the instructor leaves the classroom.
• Project: There will be no exam for the course. Instead, we will have a course project for everyone. A project will have two parts:

• Reading some papers on a particular datamining topic, which we do not have time to cover or we do not go into detail in the class, and then giving an in-depth presentation to describe and discuss the problem, objectives, data used, data analysis procedure and techniques adopted, your criticism on the existing work, and your thoughts and suggestions on possible future research.

• Designing an algorithm/method for a particular problem, most possibly from the paper(s) you read.

• Computation of the Final Grade: The following elements and scores will go into the final grade:
• Homework: 15 points total.
  
• Project:  85 points total.  (details to come later.)
  

Policy on collaboration

Please keep any discussions you have with other students to a small group of no more than 3 students and be sure that each of you are equally involved. If you just listen in and are then able to understand and write up the solution you have missed at least half of the benefit of the homework. It is really important to work through the process of recognizing when you are heading the wrong way and learning how to work through the problem solving process.

Violations of any of the above rules will be dealt with harshly! The homework problems and projects are designed to help you learn the material being taught. Being told the solution and understanding it is VERY different from working through the process of actually finding a solution. If you do not take an active role in the process of solving the homework problems and project, then you won't get much out of it, hence you won't learn the material.

Created by Weixiong Zhang, August, 2005.