For each reading, you will have one week to read the papers assigned and prepare a brief summary of your thoughts about the articles. These summaries need not be greatly detailed (unless you wish them to be), simply a few sentences that describe the main thrust of the paper, whether you think it is well presented or not, any problems you see with the presentation or methods, and any ideas of particular interest that you want to highlight. This summary must be pushed to your git repository before the start of the class a week later where we will discuss the readings.
Each discussion period will have 3-4 students designated to lead the discussion. Graduate students are responsible for extending the discussion by finding and describing an additional paper of some relevance to the topic or discussion. That additional paper should also be mentioned with a citation in their write-up. Over the duration of the course, each student will be responsible for leading the discussion at least once. When preparing to lead the discussion expect to do a deeper read of the paper, prepare some notes or visuals describing the methods, and a few discussion questions.
Reading | Data Science Topic(s) | Domain Science Topic(s) | Papers | Group |
---|---|---|---|---|
1 | Regression | Public Health and Medicine | Zhu2004 and Weng2017 | Izzy, Nimra |
2 | Classification and Clustering | Computer Science | Miller2014 and Fawcett2005 | Rahul, Orgil, Tyler, Christoph |
3 | Visualization and Knowledge Discovery | Microbiology and Statistics | McDonald2018 and Hall2019 | Ally, Holden, Parth, Srishti |
4 | Geospatial Analysis | Microbiology and Computer Science | Afshinnekoo2015 and Crandall2009 | Nick, Lakshya, Yash, Karthik |
5 | Deep Neural Networks | Computer Vision and Creativity | Varshney2019 and Redmon2016 | Jacob, Telly, Steve, Thanika |