Unsupervised identification of event-related brain potentials via competitive learning

We present a novel approach to the problem of Event-Related Potential (ERP) identification, based on a competitive Artificial Neural Net (ANN). Our approach dismisses the need for stimulus- or event-related selective averaging, thus avoiding conventional assumptions on response invariability. The identifier is applied to real event-related potential data recorded during a common odd-ball type paradigm. For the first time, within-session variable signal patterns are automatically identified dismissing the strong and limiting requirement of a-priori stimulus-related selective grouping of the recorded data. The results present new possibilities in ERP research