ABSTRACT. – The division Cryptophyta, Class Cryptophyceae, contains ecologically important species found in all kinds of aquatic habitats. Cryptophyte identification is challenged by a need to examine species in the scanning electron microscope or transmission electron microscope (SEM or TEM) to visualize morphological characters needed to identify its species. For routine monitoring programs, this group is usually identified at the level of class based on the natural orange fluorescent of their phycobilin pigments if the samples are routinely examined with a fluorescent microscope. Using analytical flow cytometry coupled with Artificial Neural Networks (ANNs), we retrained the AIMSNET ANN with 12 additional cryptophyte taxa representing several species of each of six clades in the cryptophytes. We mixed these species in different proportions and presented them to the ANN for identification as the mixture passed through the flow cytometer. Good recovery of the artificial mixture was obtained. ANNs provide yet another tool to aid in the identification of this difficult group of phytoplankton. This is in addition to the fluorescent-labelled probes previously designed for cryptophyte clades using whole cell or microarray detection. Cells not classified by the ANNs into one of its clades could be sorted and probed with those clade level markers to retrain the ANNs.