The potential of back-error propagation neural networks for identifying fungal species from flow cytometric measurements of spores was evaluated. Neural networks consisting of two, three, four, six and eight hidden nodes (processing elements) were successfully trained to discriminate between Megacollybia platyphylla, Oudemansiella radicata, Phallus impudicus, Tylopilus felleus and Fuligo septica (a myxomycete) using a training set comprising three inputs (forward light scatter, wide-angle light scatter and DNA fluorescence) for fifty spores of each species for a maximum of 500 complete presentations of the training data set (consisting of 50 different patterns per species). Hypholoma fasciculare spores were less successfully identified because the sample had been inadvertently contaminated with P. impudicus spores. Effect of size of training set and number of presentations of the training set were also examined. The potential use of neural networks in identification is discussed.