Report Requirement (answer the following questions)
1. What is the project about? Or what problems you are going to solve?
2. Which part is your own work/idea, which part is an implementation of other people’s idea, which part is using some existing code/examples?
List and cite all the reference resources (including books, papers, articles, webpages, codes and examples) at the end of your report. Using existing code or work without citation/statement will be considered as plagiarism and end up with a zero score.
3. List all the libraries/packages that you used.
4. Describe the machine learning algorithms or deep learning algorithms that are used in your project and the reason of selecting such models.
5. Provide necessary discussion or analysis of performance change using different hyperparameters (if there was any).
2. Code Requirement and Evaluation
Failure of running or downloading the code will result in a zero score for code evaluation. Code included in the submission should be “ready” to run, with proper relative path and necessary input files submitted or linked (Github links to your input datasets are acceptable when your dataset is huge.).
Well organized code with comments in it is the most important factor that determines the grade. (Jupyter notebook users need to submit your code in “.py” and make sure it is runnable on different platforms.)
Students are responsible for failure of running/downloading your code. Please include other support files that are helpful in grading in your full submission.
3. Presentation Evaluation (Peer review)
Each student needs to record a 4-minutes (or less) long presentation video, upload the video Here, watch and evaluate all the students’ presentations.
