The application of the artificial neural network for the processing of one-
dimensional micro-PIXE data is described. The network architecture, selecti
on of the transfer function as well as the training and verification operat
ions are described in detail. The performed reconstructions confirm that th
e neural network may be used for improvement of the resolution and for proc
essing of low statistics data. The limitations of the neural network applic
ation for two-dimensional images are discussed. (C) 1999 Elsevier Science B
.V. All rights reserved.