A little while ago some of the MSc students were complaining about some homework that required them to classify very bad photos of fish (from a Kaggle competition). Not sure how well they did (hopefully well). I did initially think a group of us could have a go at the problem. However Ayman suggested trying a competition about sea lions instead as they are cuter. Information can be found at https://www.kaggle.com/c/noaa-fisheries-steller-sea-lion-population-count. Essentially we would develop a method to count the number of sea lions in an aerial photo. Might not get very far in three days but it's worth a go. The only issue seems to be that the dataset is a little on the large size, so anyone with a 1-2TB HDD would be useful. Might need to download the dataset in advance due to poor wi fi at the hostel.
The Warwick Anuual Retreat Projects are back! The Warwick Anuual Retreat Projects, or WARPS as the cool crowd calls them, are study group style projects that we will work on during the retreat. The aim of these projects is to foster a collaborative atmosphere within the department, particularly between year groups. This format was debuted last year, and we hope that this year it will be as enjoyable and informative as the previous one.
If you wish to propose a project then please add a brief description of the problem you want to tackle, as a topic in the forum below. We hope that we can start a discussion on these problems before the retreat starts. Hence, others can express their interest and give comments on the projects. The deadline for project proposals is 7th April 2017.
If you like any of the proposed projects and want to join the group working on it, please specify your preference below, so we can allocate the project groups before the retreat starts. If you hate all of the projects below, then please propose one you like! This time we want to allocate projects before the start of the retreat so we allow for more time to work on the projects.
Warwick Annual Retreat Projects 2017
Counting Sea Lions
- The problem should not be part of your PhD!
- The problem proposed should ideally be simple so that someone without domain specific knowledge could contribute.
- Approximately 7 hours are allocated for these projects so progress should be possible within this time-frame.
- Groups will be expected to give an informal summary during the forum session on the Wednesday following the retreat (13:00, 10th May).
- If you propose a project that involves working with data, please make sure you have a copy of the data on a physical drive in order to save time from downloading on slow wifi.