• Syllabus
• Schedule and foils
• Reading list
• Homeworks
• Project
• Exams
  

**** NEWS and ANNOUNCEMENTS ****

• *** 12/04 ***: solutions to sample final exam are out
  
• *** 12/03 ***: HW4 solutions are out
  
• *** 12/02 ***: Final exam study guide is out (with pointer to older exam, review questions, etc)
  
• 11/20: Homework3 solutions are out
• 11/05: Homework 4 is out
  
• 10/24: 'mystery weighted-dataset' for default-project phase2
  
• 10/23: phase2 clarifications
  
• 10/8: midterm-exam preparation:
•  questions + solutions;
  
•  study guide (reading list, extra office hours, and related information)
• sample midterm exam, and solutions (internal to CMU)
• 10/7: HW3 is out
  
• 9/26: (75MB) dataset for phase1-default, is out
• 9/26: hw1 solutions are out
  
• 9/18: Homework 2 is out
  
• 9/16: Project description is out
  
• 9/2: Welcome to the class! First lecture is on Wed. Sept. 4.

Course information

• Instructor: Christos Faloutsos, ( christos @ andrew )
  • GHC 8019, cell ph (412)-576.79 three two
  • office hours: Tu 3-4pm; also, by appointment
• TA and office hours:
  • Ravi Teja Mullapudi, ( rmullapu @ andrew ), Fri 10-11am, @ 234 Smith Hall
    
• Course admin: Mr.  Tony Mareino,  ( amareino @ andrew ), GHC 7227
  
• Class meets: M-W, 1:30-2:50, GHC 4303
• URL for this very web page: www.cs.cmu.edu/~christos/courses/826.F19/

Homeworks

1. Homework1; and solutions
   
2. Homework2 and solutions
3. Homework 3 and solutions.
4. Homework 4 and solutions
   

Project

• All projects:
• Description, project list and admin info.
• Phase2 clarifications
  
• DEFAULT projects only:
  
• Dataset for phase1 
  
• Dataset for phase2
  

Exams

• Midterm exam preparation:
•  questions and solutions
• study guide (reading list,  extra office hours, and related information)
  
• older exam, and solutions
  
• Final exam study guide is out (***new, 12/02 ***)
  

Late Policy - for all deliverables:

• No delay penalties, for medical/family/etc emergencies (bring written documentation, like doctor's note).
• Each person has 4 'slip days' total, for the whole semester.
  • That is, no questions asked, if the total delay is 4 days or less.
  • 5% per day of delay, after that
• To use slip days:
  • email you material to  the TAs
  • with the subject line:     15-826 Homework Submission (HW #)
    
  • and the count of slip days you use, as well as the count of slip days left

Regrade-request policy

• Regrade requests should be done in writing/email
• within 2 days
  
• to the TA that graded the question, and specifying
  1. the question under dispute (e.g., 'HW0-Q.2.b')
  2. the extra points requested (e.g., '2 points out of 5')
  3. and the justification (e.g., 'I forgot to eliminate mirror pairs, but the rest of my answer was correct')
• in the remote case there is no satisfactory resolution, please contact the instructor.
  

Homework pick-up information

• From the course admin (Mr. Tony Mareino)
  • with photo-id (for your privacy protection)
  • M-W-Th-F 9-11am; 2-4pm
  • GHC 7227
    

Misc. resources

• ACM SIGKDD home page (the MAIN site for data mining: tools, datasets and other resources)
• KDD nuggets: wealth of information for data mining - datasets, software, jobs, call for papers etc etc.
• ACM SIGMOD home page (DBMS resources, free software, papers, conference info)
  • Michael Ley's DB bibliography server (impressive!) and its SIGMOD mirror
• DASL ( Data and Story Library - statistical tools and datasets)
• info about hadoop and PIG