Classification as unknown by rbf networks: discriminating phytoplankton taxa from flow cytometry data

摘要

Identification problems in biology and medicine are often unbounded with the number of possible classes unknown. Often it is more important to reject patterns from classes upon which a network has not been trained than to classify them incorrectly. the ability of radial basis function networks to do this is examined using flow cytometry fingerprints of phytoplankton taxa. Applying the criterion to reject if the hidden layer node with the largest output was less than 0.4, successfully rejected over 95