Akond Rahman, PhD [email protected] Foundation Hall, Room#132 Office hours: 9:30 AM – 10:30 AM , Friday
Recommended Textbook: Introduction to Data Mining, Tan, Steinbach, and Kumar, second edition (https://www-users.cs.umn.edu/~kumar001/dmbook/index.php)
| Date | Tentative Schedule |
|---|---|
| Jan 21 | Introduction, Team Formation |
| Jan 23 | Data types, Statistics |
| Jan 28 | Data Pre-processing |
| Jan 30 | Text Mining |
| Feb 04 | Association Rule Mining |
| Feb 06 | Association Rule Mining |
| Feb 11 | Sequence Mining |
| Feb 13 | Sequence Mining |
| Feb 18 | Project Presentation |
| Feb 20 | Exam#1 |
| Feb 25 | Guest lecture |
| Feb 27 | Time Series Analysis |
| Mar 03 | Clustering |
| Mar 05 | Clustering |
| Mar 10 | Project Presentation |
| Mar 12 | Guest lecture |
| Mar 24 | Graph Mining |
| Mar 26 | Graph Mining |
| Mar 31 | Exam#2 |
| Apr 02 | Project Presentation |
| Apr 07 | Search-based algorithms |
| Apr 09 | Machine Learning |
| Apr 14 | Machine Learning |
| Apr 16 | Machine Learning |
| Apr 21 | Project Presentation |
| Apr 23 | TBD, Take home exam distributed |
| Apr 28 | Data Mining in Industry |
| Apr 30 | Data Mining in Industry |
| May 05 | Take home exam due |
| May 06 | Tentative grades distributed |
- Exam#1: 25%
- Exam#2: 25%
- Exam#3: 10% (Take home)
- Project: 40%
- Some extra credit
- Final Report: 30%
- Code: 30%
- GitHub Activity-Commits, Issue discussions: 20%
- Elevator pitches or pechakucha presentations: 20%
- Each project member will give updates in front of the class
- 5-10 minutes per person for each group
- Round robin fashion
- A: 90-100
- B: 80-89
- C: 70–79
- D: 60–79
- F: less than 59
- All exams are open book, one page both side handwritten cheat sheet allowed, Cheat sheets need to be submitted with exam scripts.
- No questions on source code in exams
- Project source code must be maintained in Gitlab/GitHub repos
- If the instructor detects copy-paste in source code or exams then that will result in direct F for the course .
- Each project update will include updates so far as a Markdown file which will reside in the repo. Instructions on how to run the program in the Markdown file. The required libraries needed to run code should be written.
- Final project report should be spell-checked, typo-free, without passive voice.
- Mismatch between reported output and source code results will be inspected. The instructor will download repos, install libraries, and run the code based on the instruction provided in the mentioned Markdown file. For reproducibility teams are allowed to use Docker containers.
- Every regrade request is due within 48 hours.
- One project report