Neural Decoding Competition, 2013
We are coordinating a revolving neural decoding competition, beginning initially with a human EEG dataset. The first competition concluded, and contest winners presented their work at BIBS lunch on 3/20/14. Please see here for the Brown news announcement.
We will subsequently add other datasets, including single unit electrophysiology, fMRI, and others. The competitions are open to people at all levels (from students to faculty) at Brown University.
Information about the next competition will be found on this page shortly. Here is the information for the first competition (just concluded).
The available dataset comes from the Laboratory for Neural Computation and Cognition, and contains EEG signals recorded from humans performing a cognitive task in which they have to learn based on trial and error which button to press in response to visual stimuli presented on a computer. The challenge for this competition is to be able to decode from temporally evolving EEG signals alone, various visual and cognitive variables. There are four decoding problems:
- decode the participants’ attention to visual color vs shapes
- decode which specific colors or shapes the participants were viewing;
- decode the feedback presented to the participants after their button press (correct or incorrect).
- decode the abstract rules that participants use for organizing choices
Details of the dataset organization will be provided when you sign up for the competition, together with the data itself.
Contestants should submit a short report describing their approach, as well as the predicted values for the test sets provided. The report should be detailed enough to allow replication of the method (including the code used is welcome, but not mandatory). Specific information regarding submissions will be given at a later date.
Winners will be decided by a panel of judges, based on several criteria, including overall decoding success in the test sets (in particular, more points will be awarded for better performance across multiple sets), but also on other aspects such as innovation and creativity.
Winners will be invited to present their work at a BIBS lunch. There will also be prizes, including an iPad as first prize.
Note that people of all levels are welcome to participate. There will be separate prizes for students and all categories. Team entries are also allowed.