The natural ability of Artificial Neural Networks to perform pattern recognition tasks makes them a valuable tool in Electron Microscopy, especially when large data sets are involved. The application of Neural Pattern Recognition to HREM, although incipient, has already produced interesting results both for one dimensional spectra and 2D images.

In the case of ID spectra, e.g. a set of EELS spectra acquired during a line scan, given a “vigilance parameter” (which sets the threshold for the correlation between two spectra to be high enough to consider them as similar) an ART-like network can distribute the incoming spectra into classes of similarity, defining a standard representation for each class. In order to enhance the discrimination ability of the network, the standard representations are orthonormalized, allowing for subtle differences betwen spectra and peak overlapping to be resolved. The projection of the incoming vectors onto the basis vectors thus formed gives rise to a profile of the data set.