The mini project is carried out in groups of 3 to 4 students.
The project is to predict which songs, out of a data set of 200 songs, Andreas Lindholm will like. To your help, you are provided another data set of 750 songs, which Andreas already has labeled with like or dislike. The data consists not of the sound files themselves, but of high level features extracted from them.
Using the methods in the course, you will implement the project in Python (outside the scheduled hours), submit your final prediction to a website, and write a report. You will also peer-review a report from another group, and - if necessary - revise your own report. Outstanding work will be awarded with a gold star, which can raise your final grade.
All instructions are in this file: instructions.pdf
Please read them carefully!
The datasets are available here:
Submit your solution here (and see how well the other groups are doing). Note that you only need to submit one solution here during the entire project. (But for the sake of a fun competition, we allow you to submit up to one solution per day and group).
Clarification: The LaTeX template for NeurIPS has line numbers in its draft mode. You should not remove these numbers. They can be useful for your reviewers when they want to refer to a specific part of your report (e.g., "the equation on line 54").
The deadlines and other important dates for the project are as follows:
||Both report and contribution statement
|Peer-review (of another group's report) assignment
|Feedback and grade (pass/revise)
||Both report and peer-review report
|Revised peer-review submission
||Only if revision on peer-review is required
|Final revised report submission
||Only if revision on mini-project report is required
|Feedback on revised report
(submission deadlines are one minute before midnight, i.e., 23.59)
Group registration and submission
The group registration and the submission of the report and the contribution statement are done here in Studium.
Check list before report submission
In order to pass (or possibly even achieve a gold star if your report is written such that a thorough understanding of the methods is conveyed and has a technical contribution beyond the minimum requirements), please check that ...
- You have read the final version of the report from start to end, and made sure it is readable.
- The report does not contain material copied from elsewhere (all reports are checked for plagiarism using Urkund).
- The report is anonymous with the correct title (that also goes for the file name).
- The report is written using the NeurIPS style, and is not more than 6 pages long.
- You have written the contribution statement in a separate document which is to be submitted here.
- You have included everything listed in 4.1 in the instructions.
If you have questions, write in the discussion forum.