Statistics 352: Topics in Computing for Data Science
This course will consist of a series of group discussions on topics in computing for data science; in particular, topics relevant to the research interests of the participants. It will be a true seminar as opposed to a series of lectures.
The value of the course to participants (and the requirement for completion of it) will come from leading the discussion on one topic and participating in the discussions generally. These discussions are likely to introduce relevant techniques and considerations of how best to adapt them to areas of data-intensive science. The format of the course reflects the experience of the group of Stanford Data Science Scholars.
The course is suitable for doctoral students past the qualifying exam stage and with at least a general idea of their research direction. In particular,
students in statistics, computer science and other methodological disciplines can present a general area in which they may plan on reseraching advances;
students in doing data-intensive research in a scientific or generally knowledge-based field can explore and present a computing topic in data science that is likely to be relevant to that research.
The course is offered on a credit/no credit basis.
Important: Before start of the quarter when the course is given, anyone enrolling must obtain approval from the instructors for a suitable topic; also, do some initial preparation by reading or computational investigation on the topic. See under Requirements for details. Anyone planning to enroll in the course must follow the procedure given there.
The presentations don’t require expert level on the topic; rather, the ideal is a topic of importance to the presenter, who has done some initial investigation and takes this opportunity to explore it further. Participants should also have a basic familiarlity with computing for data science so as to participate in the general discussions.