A quantitative study of evoked potential estimation using a feedforward neural network

The authors have used a multilayer perceptron to estimate the evoked potentials, masked by the EEG signal. The problem was studied on synthetic signals and error criteria other than standard L2-norm were taken into account. The authors have shown experimentally that better results could be obtained this way, if the parameters were properly adjusted. An average performed on a few ensembles strongly improves the result and the number of ensembles is lower than quoted in other approaches. The authors have also studied the influence of the window length and of a different number of hidden units upon the convergence speed and test error. Though good results were obtained in this quantitative study, the trained network which resulted should be tested on real data, in order to get a complete outlook upon this problem