As discussed in the syllabus and in class, a large portion of your course grade will be based on your large project. That project involves choosing a topic, writing a paragraph describing that topic, doing a literature search and turning in a list of references, proposing a project, giving status reports, implementing code, collecting data, analyzing data, writing a report, and presenting your results.
All assignments are due by 11:59 PM Central Time on the listed due date, unless otherwise specified.
The first step in this assignment is to determine your topic. The topic may be any topic listed on the course schedule. Additional topics related to artificial neural networks and/or evolution are also possible, with prior approval. Please consult with me if you have an alternative idea you would like to consider.
Once you have decided on a topic, you are to write a paragraph describing, in your own words, the topic you have selected. (If you are unclear as to what it means to described something "in your own words," please read the University’s web pages on academic integrity, particularly the documents related to plagiarism.) The point of your writing this paragraph is to ensure that you have looked at your proposed topic in enough depth to make a topic selection appropriate for your work in this course.
Your topic paragraph should be approximately 100-200 words in length. (This is a guideline range. Values somewhat outside this range are acceptable. However, if you go much over 200 words, I may take off points for being excessively verbose.) You should submit an electronic copy of your topic paragraph through Canvas. Due: Monday, January 22.
The second step in this assignment is to conduct a literature search to find publications describing at least two different approaches to the topic you have chosen. (Actually, you could conduct part or all of this literature search while determining your topic. However, you are not required to turn in your list of references until after you have turned in your topic paragraph, so you may conduct the literature search second.) The approaches you decide to cover may include those discussed in the textbook. However, you must find where those approaches were originally published in the primary peer reviewed literature and use those publications for your projects.
|
The primary literature consists of papers, articles, tech reports, etc. written by researchers about their own research (whether engineering, scientific, and/or mathematical). The primary literature can be distinguished from the secondary literature of the field, which is comprised of publications such as surveys and reviews. These are considered secondary contributions to the research literature because they summarize and organize the primary literature for the research community. These also contribute to the research community, but in different ways than the ways in which primary research publications do. Going further, we have the tertiary literature, which includes textbooks and tutorials. Like the secondary literature, the tertiary literature tries to summarize and organize the literature of the field. However, unlike the secondary literature which is targeted toward the existing community of researchers and is intended to help move the field forward, the tertiary literature is aimed toward people with little or no experience in the field (such students or researchers from other fields). Consequently, it tries to simplify the presentation of the material and amplify its central issues. While the secondary and tertiary literature can help you to understand the field, and you are encouraged to explore this literature for this reason, your project and tech paper reviews must be based on the primary, peer-reviewed literature of the field. |
You will need to find at least one publication describing each approach. The exact number of publications you use is up to you to determine. If you find a single publication that describes an approach in sufficient detail for you to get a good understanding of how it works, that one publication is sufficient. If you discover that the one publication you have found on an approach is insufficient for you to understand that approach, however, then you'll need to find more publications on that approach or move on to another approach.
The publications you use must be refereed technical publications. These include conference papers and journal articles (whether published in print or on the web) but not popular sources such as non-refereed magazines (e.g., Discover Magazine) or un-refereed sources (such as most web sites, even for departments or labs). Moreover, conferences or journals used should be professional conferences or journals, rather than student conferences or journals. It is okay if some or all of the authors of your selected publications are students—they often are in professional publications! However, the conference or journal should be one in which professionals regularly publish. If you are in doubt about a possible source, you should check with me before using it.
Turn in complete citations for these two approaches. Here are guidelines for what a complete citation includes.
You should submit an electronic copy of your references through Canvas.
Along with your references, please submit a new copy of your topic paragraph, whether or not you have changed/refined it from your original submission. In your submission, indicate whether your topic paragraph has been modified and, if so, be sure to briefly indicate the modification(s).
Due: Friday, January 26.
The third step in this process is to write a project proposal. Your proposal should extend your topic paragraph by explaining:
Your project proposal should be approximately one to two pages in length. (This is a guideline range. Values outside this range are acceptable. However, if you go much over two pages, I may take off points for being excessively verbose.) You should submit an electronic copy of your topic paragraph through Canvas.
You will submit both a draft and final version of your proposal.
Along with your proposal, please submit a new copy of your topic paragraph and references, whether or not you have changed/refined them from your original submission. If your topic paragraph and/or references have been modified, please be sure to briefly indicate the modification(s). When you submit your final proposal, please indicate if it differs from your draft proposal and, if so, what those differences are.
Draft Due: Thursday, February 1. Final Due: Tuesday, February 20
Once your proposal has been accepted (perhaps with modifications), you should start to carry out your project. To help to ensure that you are on track with your project, you will write up a brief project status report.
This status report should begin with your chosen and approved topic and include all the components required for the proposal (why the topic is interesting, what question or problem your project addresses, how you will attempt to address this question or problem, and what sort of activities you will carry out for your project) and references to at least two different approaches to your topic. In addition, you should explain where you are in carrying out your project activities and what you have learned so far from developing your project and carrying out project activities.
In your status report, be sure to answer the following questions:
Notes on your status report:
You should submit an electronic copy of your status report before class through Canvas. Status Report Due: Tuesday, April 2.
You will submit both a draft report and a final report for your project. Both versions have the same required contents. In addition, your final report will be accompanied by brief explanations of how your final report addresses each the shortcomings noted in my feedback on your draft report. The draft report is intended primarily to allow me to provide you with feedback that you can use to improve the quality of your final report. The final report will be point graded.
Your report will be modeled on a technical report that might be published by a laboratory. This will have the same basic structure as a conference paper or journal article but without requiring the fancy formatting or severe page limits. Your report will have the following components:
Title Self explanatory.
Author Self explanatory.
Abstract The abstract gives an overview of the entire work. It should state the purpose or central question of the project, state why it is important, give a brief statement of what was done, a brief statement of what was found, and a brief statement of what was concluded. It should be understandable without the reader needing to read the entire report. One good structure is to have five sentences, covering the following:
The abstract should stand alone; that is, the reader should not need to read the rest of the document to understand the abstract and the abstract should contain no citations.
Introduction The introduction covers the motivation, nature, and scope of the report. It also introduces the approach in broad terms, gives a broad overview of the results, and outlines key conclusions. It should include discussion of pertinent literature to help readers understand these elements. (How is your research similar to and different from other research in motivation, nature, scope, results, etc.?)
Note that the introduction should not replicate the abstract. However, like the abstract, it should introduce the ideas to the reader and should not assume that the reader has just read the abstract. Unlike the abstract, the introduction can (and probably should) contain citations.
Also, note that the introduction only introduces related work, your approach, your results, and your conclusions. You should cover these topics in greater depth later in your report.
Approach/Methods You need to clearly state your approach starting broadly and then filling in details until your entire methodology becomes clear. This may include text, equations, figures, pseudo-code, or some combination of all of these. The level of detail should be sufficient for other researchers to reproduce your results and carry out your analyses without needing to look at or make use of your actual code. (Note that you will be submitting an electronic copy of your code. However, the code itself does not belong in the approach/methodology section of your report. It could be included as an appendix, which would mean that you would not need to turn in a separate copy of the code.)
Results You need to summarize results from your experiments in your report. These should be thorough, so that your readers can analyze them and come to their own conclusions based on them. At the same time, these results should not be exhaustive. That is, they should not be the raw data but appropriate summaries of that data, such as medians, means, standard deviations, and results of statistical hypothesis tests run on the data. Tables and graphs are often appropriate ways to present summarized data but other summaries, such as text descriptions, may also be appropriate. Raw data may be included in an appendix.
Discussion You need to discuss the results you have found. This includes comparing your data sets to one another, comparing your results to results published in the literature (with appropriate citations), and commenting on likely reasons for similarities and differences found.
Conclusions You need to decide what is reasonable to conclude from your results and clearly state all such conclusions and the bases on which they rest.
Future Work You need to suggest appropriate ways that your work could be built upon (by you or others). This could be anything from more experiments to help validate the conclusions to radical changes in approach.
Bibliography You need to present a full set of references for all works cited in your report. Do not include other related work that is not discussed in your report.
Appendices If there is important information that you would like to include in your report that would impede the normal flow of the report if included elsewhere, it may be included in one or more appendices. In particular, code and/or raw data may be included in appendices or they may be submitted separately. Do not make duplicate submissions of these items, however.
Note that while all of the components above must be included in your report, they do not necessarily need to be organized into sections this same way. For example, if your approach combines ideas from multiple prior approaches, you might describe the approach in a single section with multiple subsections or, alternately, in multiple sections. As a second example, you might choose to combine your discussion and conclusions into one section or to combine your conclusions and future work into one section. However, deviations from the expected order and division of the document should be justifiable, not gratuitous.
You should submit an electronic copy of your report through Canvas. Draft Report Due: Thursday, April 18. Final Report Due: Thursday, May 2. In addition, your final report will be accompanied by brief explanations of how your final report addresses each of the shortcomings noted in my feedback on your draft report.
You must also present your results to the class. You will do these in the form of a technical presentation similar to the one you will do for the Technical Paper Assignments. The difference here is that this presentation will be of your own work, rather than of someone else’s work.
Students will have the option whether to present their project to the class during the final week of classes (Tuesday, April 30 or Thursday, May 2) or during the final exam period (Friday, May 10).
You should submit an electronic copy of your final slides through Canvas. Draft Slides Due: Tuesday, April 9. Final Slides Due: Tuesday, April 30. 8:30 am.
Finally, you will listen to at least 10 of your classmates' presentations and provide brief responses to them. You may choose which 10 presentations to review. You will be given a review form with a few simple questions for you to answer to complete these reviews (e.g., "What is the domain or application of the project being presented?"). Due: Friday, May 10.