You 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 your 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 artificial evolution. You will turn in draft reviews that I will examine and use to provide feedback that you should use to improve your reviews for their final versions. These reviews may be integrated into your Large Project if the topics are related. Likewise, you will turn in a draft set of slides for the technical paper presentation and I will provide feedback that you should use to improve your final slides.
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.
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.
You will write two reviews, describing two different approaches to your topic. For reach review, you need to write an approach summary and a critical evaluation.
The approach summary will include these points:
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. (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.)
Your critical evaluation should contain the following components:
For the critical evaluation, you should explicitly list, describe, and justify the evaluation criteria you are using in your evaluations. In addition, you should make clear in your review where these criteria, plus all criticisms, praise, suggestions, or other commentary originate. For example, you might use evaluation criteria from the course textbook(s), topic-specific criteria suggested by the author(s) of the paper(s) you are evaluating, general computer science evaluation criteria such as run-time complexity or space efficiency, and/or your own evaluation criteria. For each criterion chosen, you must describe and justify it and must give credit for the criterion, as appropriate. In the evaluation using these criteria, you must make it clear whether each part of the analysis is your own or is based on someone else’s prior analysis. (For example, if the authors of the paper claim their method has a particular advantage and you are echoing their claim, that needs to be clear in your review. Otherwise, it will be assumed that all claims made are your own, which would be dishonest if that is not the case.)
The internal evaluation is an evaluation of the approach, not an evaluation of the presentation of the material nor of the quality of the research conducted. For example, if you explain that the approach is (or isn't) efficient with respect to time or space, that is an evaluation of the approach and would likely be appropriate for your review. If, on the other hand, you explain that the paper is (or isn't) well organized, that is an evaluation of the presentation of the material. It is okay to note presentation issues in passing but they should not be the focus of your review. Similarly, if you explain that the experiments in the paper were not repeated sufficiently many times to obtain statistically meaningful results, that is an evaluation of the quality of the research conducted. It might be important to note such issues as they effect your ability to judge with respect to other criteria (e.g., it might be difficult to know if an approach is effective in such as case) but such issues should not be considered evaluation criteria on their own.
The critical evaluation should run from 3 to 4 pages in length at roughly 80 characters per line, 25 lines per page. (Again, this is a guideline range.)
You should submit an electronic copy of your draft reviews through Canvas. Due: Friday, October 5.
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. In addition, your final reviews will be accompanied by brief explanations of how your final reviews address each the shortcomings noted in my feedback on your draft reviews. You should submit an electronic copy of your final review before class through Canvas. Due: Monday, November 5.
For your presentation, you must prepare draft slides.
You should submit an electronic copy of your draft slides before class through Canvas. Due: Wednesday, October 17.
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 Canvas. In addition, your final slides will be accompanied by brief explanations of how your final slides address each the shortcomings noted in my feedback on your draft slides. Due: Monday, October 29, 1:00 pm.
You must also actually present your review to the class. The presentation dates are Monday, October 29 through Monday, November 12. As stated previously, your presentation will be 15 minutes long with up to 3 minutes for questions and answers. 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.