ITEC560 - Projects

|ITEC560Course Outline |ResourcesAssignments |Projects | Marks | Announcements |


A small, focused project will be done over an approximately one month period at the end of the semester. Students will form groups of 1, 2 or 3 by self-organization. The purpose of the project is to enable the students to get some hands-on experience in the design, implementation and evaluation of neural network algorithms by applying them to real-world problems.

The project will be an implementation / examination of some particular aspect of a neural network algorithm, or it will show the application of an algorithm on a particular problem. You can select data sets from the list of data resources available.

You should submit a 1-2 page proposal that describes the problem you would like to tackle, objective of the study, proposed algorithms, hardware/software tools and data that you plan to utilize, and evaluation strategies that you plan to use. You should get prior approval before starting your project.

You are free to use any programming language or toolbox but Matlab is strongly recommended. You can write the codes yourself or use any code that is available in the public domain. In case you use somebody else's code, you are required to properly cite its source and know the details of the algorithms that the code implements.

You should submit a readable and well-organized report that provides proper motivation for the task, proper citation and discussion of related literature, proper explanation of the details of the approach and implementation strategies, proper performance evaluation, and detailed discussion of the results. Highlight your contributions and conclusions. Also submit well-documented software with your report. The reports are expected to be 6-8 pages and must follow the IEEE Computer Society two-column format as described in their templates. Try to follow the format as closely as possible. It should be submitted as a pdf.

The Project Report should have the following format: 

Introduction: Describe your motivation for studying this topic, and any relevant background for this problem.

Statement of Problem:  a brief one-paragraph statement indicating what the problem is that you propose to implement or demonstrate. Contributions of the group members must be clearly stated in the report.

Objectives: a brief statement of what you expect to achieve in relation to the Statement of Problem, e.g., a working algorithm, a demonstrated classification of data, model fitting, information discovery, etc.

Technical Approach: outline of the methods for achieving the Objectives, including description of the data used.

Results: substantiation and discussion of the results achieved, in comparison to the initial Objectives. Graphical presentations are frequently better than tables and sentences.

Conclusions: Briefly summarize the important results and conclusions presented in the report. What are the most important points illustrated by your work? In what kind of problems the proposed solutions can be used.

Appendices: pertinent supporting material, the other supporting materials such as code; and optional items, e.g., data, extra plots etc. should be submitted separately.

Projects will be presented to the class. The presentation will be approximately 10-15 minutes, with 5 minutes left over for question-and-answer from the class. Slides made in a commonly used format (i.e. PowerPoint) can be used. Each student is expected to attend all presentations. An electronic copy of the Project Presentation should also be submitted. 

The presentation will be evaluated on the following items:

Appearance of presentation.

Organization of presentation.

Description of project and stating the objectives.

Relevant background material.

Description of methodology.

Description of implementation issues.

Comments on the results. 

Duration of presentation.

Individual performance.

Response to questions / Question handing.

Projects Grading (25%)

Evaluation and Grading Proposal Documentation/Report Presentation
Percentage 5%10 %10 %