CS 5970 — Technical Paper Assignments

NOTE: With a few exceptions (noted below in italics), each part of this assignment, like other assignments in this class, is due at the beginning of the class period. This means that if you are even a minute late, you lose 20%. If you are worried about potentially being late, turn in your completed assignment ahead of time. Do this by submitting it to me during office hours or by sliding it under my office door. Do not send assignments to me through email or leave them in my departmental mail box.

Each student will review in writing two approaches from the technical literature and will present one of these approaches to the class. These approaches may be related to the student’s Large Project but they are not required to be. All technical papers must come from the primary, peer reviewed literature in artificial neural networks and/or evolution. Each student will turn in a draft review that will be examined by the instructor who will provide feedback that the student should use to improve his or her review for the final version. This review may be integrated into the student’s Large Project if the topics are related. Likewise, each student will turn in a draft set of slides for the technical paper presentation and the instructor will provide feedback that the student should use to improve his or her final slides.

Topic Paragraph

The first step in this assignment is to determine your topic. This may be the same topic as the one for your Large Project or it may differ. If you choose the same topic for both assignments, you should only turn in one topic paragraph and label it as covering both assignments. If you choose separate topics for these assignments, you should turn in two separate topic paragraphs, labeled accordingly. In either case, follow the directions in that assignment in completing your topic paragraph.

References

The second step in this assignment is to conduct a literature search. If you have chosen the same topic for your Large Project and for this assignment, you should only turn in one list of references and label it as covering both assignments. If you have chosen separate topics for these assignments, you should turn in two separate lists of references, labeled accordingly. In either case, follow the directions in that assignment in completing your list of references.

Draft Reviews

You will write one review for each approach.

• Approach Summary. You are to write a summary that includes the main ideas behind the approach. This summary does not need to compare this approach to any other. However, it should be detailed enough that a reader familiar with different approaches to the same topic should be able to recognize that the approach you are summarizing is, in fact, different.

  The approach summary will include these points:

  1. The domain/application.
  2. The problem to be solved or question to be answered.
  3. The motivation for solving this problem or answering this question and why artificial neural network and/or evolutionary approaches are involved.
  4. The hypothesis, if appropriate.
  5. The approach and methodology.
  6. The experiment(s).
  7. The results.
  8. The conclusions.
  9. Future work.

  Please Note: Taking the first line or two from each paragraph in a paper, stringing them together, and changing around a few words here or there to make things read better, is NOT a summary. It is plagiarism—a form of academic misconduct. Any time you quote a source, you must include the quotation in quotation marks and clearly indicate the source of the quotation. If you find yourself with more than a couple of brief quotes in each summary, then you are quoting too much. To summarize a paper, you need to (1) read it, (2) understand it, and (3) briefly relate its main points in your own words. If you don't have your own words to describe the approach, that probably means that you don't understand the paper—you'll need to go back to steps 1 and 2 and visit me during office hours as needed to help you with step 2. (I don't expect most students to have problems understanding the difference between a summary and plagiarism. This message is for those few who do.) Again, if you don't understand what it means to describe something "in your own words," please read the University’s web pages on academic integrity, particularly the documents related to plagiarism.)

  The summary should run from 3 to 4 pages in length at roughly 80 characters per line, 25 lines per page. You should double space this document, so that I have room to write comments/corrections on it. (Again, this is a guideline range. Values somewhat outside this range are acceptable. However, if you go much over 4 pages, I may take off points for being excessively verbose.)

• Critical Evaluation. Once you have summarized the approach, you should give a critical evaluation of it. The term 'critical' here does not mean negative. Rather, it means, like any good critic, you should thoroughly evaluate the approach, in a principled way, and give your best judgment as to its strengths and weaknesses. The critical evaluation is worth half of the review points and should be extensive.

  The critical evaluation should run from 3 to 4 pages in length at roughly 80 characters per line, 25 lines per page. You should double space this document, so that I have room to write comments/corrections on it. (Again, this is a guideline range.)

You should submit an electronic copy of your draft reviews before class through D2L and turn in a printed copy at the start of class. Due: Monday, February 25.

Final Reviews

The final reviews will consist of all the same elements as the draft reviews. However, because you will have received feedback based on your draft reviews, the final reviews should be of higher quality. You should submit an electronic copy of your final review before class through D2L and turn in a printed copy at the start of class. Due: Monday, April 8. When you submit your paper copy of your final review, you must also resubmit your graded paper copy of your draft review.

Draft Technical Presentation Slides

For your presentation, you must prepare draft slides.

• Your presentation will be 15 minutes long with a discussion period of up to 10 minutes.
• You should use no more than 15 slides during your talk (although you may prepare additional slides for use during the discussion period).
• The review presentation will cover these points:
  1. The domain/application.
  2. The problem to be solved or question to be answered.
  3. The motivation for solving this problem or answering this question and why artificial neural networks and/or evolutionary methods are involved.
  4. The hypothesis, if appropriate.
  5. The approach and methodology.
  6. The experiment(s).
  7. The results.
  8. The conclusions.
  9. Future work.
  10. Discussion questions. You should have at least five questions that you can ask of the other students in the class to spur discussion. These should be included in your slides but do not count toward the 15 total for the presentation.
• Make the slides high-contrast. (No white letters on a pink background or vice versa.)
• Keep each slide simple. Limit each slides to a few list items, one equation (or two very simple equations), a simple figure, or a table with very few columns and rows. There is no need to try to put your entire paper on a slide or to try to spell everything out in great detail. You will be talking and can provide sufficient detail with what you say. The slides should be for main points only. Allowing the slides to ramble on and on, or to contain excessive repetition, or other similar problems, will only detract from their usefulness. While I am grading you on your slides, I don't need them to explain the whole of your paper to me. I have your paper for that. The purpose of your slides is to support your talk. Blah, blah, blah. Do you get the feeling this is getting longer and longer but not saying anything more? Well, okay then; do not make your slides like this paragraph. Make them like the opening sentence or two, which had all of the points without all of the words.
• Have an overview slide near the start of your talk and a review or summary slide near the end.
• If you use colors, use them for important points only. They should not distract your audience.
• For additional ideas on how to give a good presentation, see my presentation on how to give a good technical presentation.

You should submit an electronic copy of your draft slides before class through D2L and turn in a printed copy at the start of class. Due: Monday, March 11.

Final Technical Presentation Slides

I will provide you with feedback on your draft slides to aid you with your revisions. You should submit an electronic copy of your final slides before class through D2L and turn in a printed copy at the start of class. Due: Monday, April 1, 3:00 pm. When you submit your paper copy of your final slides, you must also resubmit your graded paper copy of your draft slides.

Technical Review Presentation

You must also actually present your review to the class. The presenation dates are Monday, April 1; Wednesday, April 3; and Monday, April 8. As stated previously, your first presentation will be 15 minutes long with up to 10 minutes for discussion. I may call on you to give your presentation on any of the scheduled presentation days. I will not announce the exact presentation schedule ahead of time. This means that you will need to attend class all of these days and be ready to present when called on. You will not be graded on your actual speaking (except that you will lose points if you fail to give a presentation). The presentation grading will be for the slides. As stated above (under "Final Technical Presentation Slides"), you will need to turn in the final draft of your slides for grading.