Neural network classification of event related potentials for the design of a new computer interface

A discussion is presented of the classification of single event-related potentials (ERP) with a neural network classifier. The purpose is to discriminate the YES and NO answers thought by a computer user in response to words flashed on the computer display and to assess the feasibility of building a computer interface called the cortical mouse. The performance of the neural network is compared with a classifier using an eigenvector-based extraction method. The neural network outperformed the other classifier. For some subjects the classification is above 90%, but the introspected variability is still large