CSCI 397 (F '14), Seminar: Techniques in Big Data (DRAFT...)

Overview
   Techniques in Big Data: The term "Big Data" encompasses the acquisition, analysis, and visualization of high-dimension, high sample-size data to inform decision making -- problems with many dimensions and many samples make for "Big" problems. However, "Big" also refers to the central role of Big Data analysis in our daily lives, where it affects outcomes in medicine, security, advertising and recommendation systems, transportation, and many other domains. In this course, we learn and apply some of the field's core algorithms and techniques, with an emphasis on three application domains agreed upon at the beginning of the term. Specific technical topics may include feature selection, linear and Bayesian discriminants, principal component analysis and dimensionality reduction, clustering, neural networks, and random forest learning.

Is This Class For You?

1. This is an upper level CS elective, and as such you should expect to spend at least 12 hours per week outside of class on everything from reading to debugging.  You are also expected to show considerable agency in problem solving.
   

Textbooks
Required:  Pieces from data mining, distributed systems, databases? .
Optional:    .

Attendance, Grading, Late Assignments

1. Attendance is required.
2. Grading breakdown: Tests 30%, Quizes 20%,  Projects 2x10%, Homeworks 20%, Attendance and Participation 10%.
3. Grade cutoffs: A+: 97%, A: 93.5%, A-: 90.0%, B+: 86.5%, B: 83%, B-: 80.0%, C/D (see B minus 10 or 20)
   
4. There will be two group projects.  Late submissions of any sort are not accepted, with these notes:
   
• I will defer to the Counseling Center (see here).
• If you have an athletic event and will not be able to make a deadline, you should tell me within a day of an assignment being posted.
  
• Accomodations for qualified disabilities requires written notfication in conjunction with Dean Bell of Student Academic Support (see here).