A. Lopez-molinero et al., Classification of ancient Roman glazed ceramics using the neural network of Self-Organizing Maps, FRESEN J AN, 367(6), 2000, pp. 586-589
Artificial neural networks with unsupervised learning strategy known as Sel
f-Organizing Maps were applied to classify ancient Roman glazed ceramics. T
heir clay ceramic bodies were analyzed by Inductively Coupled Plasma-Atomic
Emission Spectroscopy and the chemical composition obtained was processed
by this neural algorithm. The results obtained provide two types of informa
tion: firstly, classification of ceramic samples with identification of sev
eral groups and secondly, differentiation between the elemental chemical in
formation. It was found that there are certain chemical elements which can
be considered as principal and which can serve to differentiate between cer
amics, whereas other elements give redundant information and do not contrib
ute to sample differentiation. Seven chemical elements were considered prin
cipal and provide the necessary information. Two types of element were iden
tified: 1 - a group formed by common elements, such as: Ca, Fe, Mg, Mn and
2 - another formed by optional elements: K or Na and Ba or Sr and Al or Ti.