The term project reports are due on April 23, 2020 at 1:00pm. A project report should be organized like a conference paper with abstract, introduction, related work, methodology, experimental results, discussion of results, and conclusion sections.

Term project formatting The term project report format is flexible, you can use either a single column or double column format. Also there is no target page length. The completeness of the report would be judged by its content.

The term project reports should be self-explanatory. This means that the key parts of the text, description of the methods and their justification should be included in the report. In other words, the report should be written is a way the content is possible to understand without going to and reading other works/literature the report refers to. For example, a sentence like: "we implemented and tested WonderML method [reference]" without further explanation and a brief description of the method are not sufficient and (not !!!) self-explanatory.

References Please do not forget to give the credit whenever it is appropriate. Give relevant references to past work on methods or works that use the same dataset. If your implementation relied on the existing code please do not forget to acknowledge the source.

Code The code you have developed (not the data !!!) should be submitted in the zip file together with the report in the code subdirectory. Please include a brief readme.tex file explaining the main function/pieces of the code you have developed and submitted. Please acknowledge any code/packages used to develop the models or the ML algorithms.

The term projects are individual projects and all students will be in addition to the report asked to present the project during the class on April 21, 2020 or on April 23, 2020. The order of the presentations and the instructions for preparing the presentations can be found here.

Possible conflicts
In general, the project selected for CS 2750 should not be the same or overlap significantly with projects used to satisfy requirements of other courses (e.g. vision, image analysis, pattern recognition or NLP courses) Please note that any possible conflict should be discussed and approved by the instructors of both courses prior to the project.

Here is a link to the Intro to ML in python document that provides a guide to building ML solutions with the help python libraries. Please note this document is under development and is likely to be updated and refined periodically.