Ignorance-based signal estimation given multiple noisy realizations

We previously reported that decision systems in speech and biomedical waveform processing had been enhanced through the use of iterative "ignorance-based" statistical pattern recognition techniques [1]. Here we discuss the extension of this approach to estimation of a stochastic signal buried in noise given an ensemble of realizations. As before, there are minimal assumptions based on prior knowledge. The successful application of this method to the estimation of event-related brain potentials is described.