Neural network signal processing in human brain research. II. Applications

For pt.I see ibid., vol.10, pt.3, p.1494 (1988). Summary form only given. The author has used a two-layered neural network algorithm with hidden units and backwards propagation of error to extract features and perform classification of human EEGs and evoked potentials. The clinical outcome of neurosurgery has been predicted, the neurological effects of different types of sleeping pills have been differentiated, and insights have been gained as to how brains produce higher cognitive functions.<
>