CSCE 478/878 (Fall 2016) Project Ideas
In this course you and your homework teammate will do a substantial project.
This project can be:
(1) an extensive literature search and summary on a particular
topic, (2) a good implementation and evaluation of a known result in
machine learning, or (3) a small (but nontrivial) amount of original
research related to machine learning.
You will summarize your project results in a written report and an oral
presentation. The written report must
use a professional writing style similar to that found in an ACM or IEEE
journal, including abstract, introduction, summary of related work, your
contribution, references, and an appendix (if necessary). The oral
presentation
will be to the entire class at the end of the semester: during the fifteenth
week (December 5–9), and if necessary, during the fourteenth week
(November 28–December 2). You will submit your written report to
us no later than 11:59 p.m. on
December 7
December 14.
In accordance with UNL policies,
you have now been informed in
writing of the nature and scope of this project prior to the eighth week
of classes.
Later this semester (late September to early October) we will set a deadline
for submission of 1–3 paragraph proposals on your projects. You must do this
in order to get full credit for your project, and you must get our approval on
it before starting work on your project.
we will provide a list of possible topics later this semester, but you
may propose your own topic as well. To be a valid topic,
it must go beyond the scope of the course.
Your project could be on
a topic we did not cover in class at all, or could more deeply explore
a topic we covered in class.
DEADLINE:
The proposal submission deadline is Sunday, Oct. 9. You
should submit it to me in text format in the body of an email before 11:59 pm on that day.
The proposal should include:
- A brief statement of your project topic.
- Motivation for your topic (why it is important and interesting).
- A precise work plan: what you plan to do, what data sets you will test on, how you will evaluate performance, etc.
- At least 3 references (at least two published journal or conference papers).
DEADLINE:
Projects are due by
11:59 pm
on
Wednesday, December 7
Wednesday, December 14,
submitted via handin.
- Schedule of project presentations
-
Rules on projects, a.k.a. what
to turn in for your proposal and for your final project writeup
-
Tips on Presenting
Technical Material
- Sources of project ideas:
- If your thesis research or a project you are doing
for another course is appropriate for this course's project, I may allow you to
use it for this course. However, you still need to submit a proposal.
- See this list of
ideas, including project ideas from other CSE faculty.
Some of these could be turned into research projects, e.g. a thesis
or project for MS or BS.
- Check the projects done in the following previous offerings of CSCE 970
(Pattern Recognition)
and CSCE 478/878 (Machine Learning). You may choose to expand on one of these
projects.
- CSCE
970, Spring 1999
- CSCE 970,
Spring 2001
- CSCE 970,
Spring 2003
- CSCE
970, Spring 2007
- CSCE
478/878, Fall 1999
- CSCE
478/878, Fall 2001
- CSCE
478/878, Fall 2003
- CSCE 478/878, Fall 2004
- CSCE 478/878, Fall 2006
- CSCE 478/878, Fall 2008
- CSCE 478/878, Fall 2010
- CSCE 478/878, Fall 2012
- CSCE 478/878, Fall 2014
- Look at projects done in other machine
learning courses. However,
if you choose such a project, please do not contact the instructors or TAs of
these courses without talking to me first!
If you think one of these ideas is interesting, send me a proposal just like
you would with any other project idea. Then, if necessary, I will contact the
instructor of that course for more information.
- Look at the "Notes" sections at the end
of each chapter of the textbook and of Mitchell's book.
- Review papers from recent conference proceedings and journals.
- See this
survey paper by Tom Dietterich on current research directions in machine
learning [from AI Magazine, vol. 18, no. 4, pp. 97-136].
Return to the CSCE 478/878 (Fall 2016) Home Page
Last modified 01 December 2016; please report problems to
sscott AT cse.