CS 151: Artificial Intelligence
Final Project
Due dates: 12/10/13 and 12/20/13 in-class
|
Final Project Details
In this class, we've studied a number of foundational topics
in AI (search, CSPs, games, probabilistic reasoning, machine
learning). The purpose of the final project is for you to
explore a topic we've covered (or not covered but related to
AI) in more depth.
Again, it is strongly recommended that you work in pairs or
triples. Here are some guidelines for the final project:
- You can develop a technique or an application, or
both. For example, you might propose to implement
approximate inference for Bayes nets, or you might build a
naive Bayes spam filter.
- You may use any resources you can find, including code you have
written for this class or other classes, code provided with the book,
data you find on the web, etc. Just be sure to cite any resources.
- You should be able to find at least two papers in the literature
that relate to your project. These papers should be on work that
solves the same or a similar problem.
- You should aim for a project that will take about 20 hours of
work per team member. This is not a lot of work, and things
always take longer than you expect, so try to be conservative in what
you say you will do (you can always extend it if you have extra time).
|
Should already be done
At this point, you should (1) already know who you'll be
working with, (2) already know what problem you'll be working
on, and (3) have read at least one paper (and written a
literature review) that is related to your project topic. If
you haven't done items (1)--(3) above, you
should plan on doing so before Thanksgiving!
|
Project Updates due 12/10/2013
On December 10th, we will have in-class project
updates. Each group will speak for (TBD) minutes and will
submit a rough draft of their final write up. The goal of
these presentations is to help you clarify your problem
and your approach and to ensure you don't wait until the
last minute to do all of the work.
In-class Project Updates [50 points]
For the in-class project updates, you can choose to just
speak, use the white board, or prepare a short (e.g. one-slide)
presentation summarizing your project. Regardless, your
project updates should include:
- A clear statement of the problem
- A clear outline of the steps that you have, are, or will take
to solve the problem. For example, "We've already scraped the
data we'll be using from website X and website Y. Now that we
have the data, we're working on
extracting certain features: describe features
here. Then, we're going to be using classifiers provided on
website Z to do the classification. We'll evaluate our system
by computing precision and recall on a set of held out data
points".
- A timeline of the remaining steps to be done for your project
After each group presentation, the class (and professor) will
ask questions intended to help you clarify and tighten your
projects.
Rough draft of final write up [50 points]
In addition, each group will hand in a rough draft of the
final paper. Your final papers will be typed in LaTeX using
the AAAI LaTeX template (see below). I highly recommend you
write your rough draft in LaTeX using this template. Your rough draft should include:
- The title of the paper along with the names of the
authors (i.e. team members)
- A 1-paragraph description of the problem you will
solve. (To be turned into an Introduction section)
- A 1-3 paragraph description of how you plan to solve the
problem. (To be turned into a System Description section)
- What results you aim to obtain and how you will evaluate your
approach. (To be turned into a Results section)
- Citation information for any relevant literature. (To be
turned into the Bibliography)
|
Final project presentations and paper due 12/20/2013
We'll be using our finals time slot to do project
presentations. Our time slot is December 20th at 9am which is
the final due date for the projects. The location is TBA.
Group Presentations [50 Points]
Each group will give a short (12 minutes + 3
minutes for questions) presentation. Your presentation must
include the following information:
- Why should I (or anyone else care) about what you did?
(i.e. motivation)
- What specific technical problem did you solve?
- How did you solve this problem?
- Why did you choose this solution?
- How well does it work (and how do you know)?
Your presentations will be graded on:
- Content (How well did you address each of the points above)
- Organization
- Speaking style
- Your attendance at all presentations
Final Papers [100 points]
Each group will submit a single paper for the final
project. I don't need to see any code. However, your paper
must be complete enough, and clear enough, that I (or anyone
else) could fully understand and replicate what you did.
Use the AAAI LaTeX template for formatting your papers. You can
get the
template files from the AAAI authors site
and use them for your paper format. Your paper should be no
more than 3 pages. Keep in mind that
writing a paper this short takes work and planning.
The following are common sections found in research papers:
- An Introduction that motivates and describes the problem
and the results at a high level.
- A Related Works section that briefly describes
existing work that solves the same (or similar) problem.
- A Background section that explains any
background information necessary to understand the problem
or your approach.
- A System Description section that provides the
details of how you constructed your system, how it works,
and how you tailored the algorithms described in the previous
section to the problem at hand.
- A Results section that describes how well the
system performs. A format that often works well here is
to first explain your evaluation techniques, provide their
results, and then explain those results and what they
say about the problem and about your approach(es) to it.
- A Conclusion, usually very brief, in which you can
summarize your system and the results. In addition, this
is a chance to be less scientific in your opinions about
the project and a chance to put it
in the larger context of larger, more general problems
(such as the general vision problem or a broad subfield).
You will be graded on:
- Creativity of your project and approach.
- Quality of your implementation (including how well you
evaluated your approach)
- Clarity of your paper
- More guidelines may be added here to address your specific project.
|
Submission Instructions
You will be turning in both an electronic copy and
a hard copy for your paper rough draft (due 12/10/2013 by class start at 9:35am) and your final
paper (due 12/20/2013 by class start at 9am). The electronic
copies can be submitted using the webdropbox.
The hard copies must be submitted in class.
|