The Sixth Annual Mlsp

For the Sixth Annual Machine Learning for Signal Processing competition, which is sponsored by Nokia and PASCAL2, entrants were asked to develop a classifier, with optional feature extraction, that uses only electroencephalography (EEG) data collected during an image presentation (visual oddball) task and optimally determines whether each image presented to a user contains or does not contain a prespecified target. In this paper, we (the organizers of the competition) briefly describe the application, the data, the rules, and the outcomes of the competition. A total of 35 teams entered the contest. Training data were provided. The entries were tested using disjoint test data, to which the entrants did not have access. The three teams whose entries produced the largest value for the performance metric describe the approach they used in three separate companion papers, all of which appear in this year’s conference proceedings. The first place team, whose entry produced an area under the receiver operating curve of 0.82, consists of Jose M. Leiva (University Carlos III de Madrid) and Suzanne M.M. Martens (Max Plank Institute for Biological Cybernetics).