A. Roy et al., A NEURAL METHOD FOR DETERMINING ELECTROMAGNETIC SHOWER POSITIONS IN LATERALLY SEGMENTED CALORIMETERS, Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment, 364(3), 1995, pp. 524-530
A method based on a neural network technique is proposed to calculate
the coordinates of an incident photon striking a laterally segmented c
alorimeter and depositing shower energies in different segments. The t
echnique uses a multilayer perceptron trained by back-propagation impl
emented through standard gradient descent followed by conjugate gradie
nt algorithms and has been demonstrated with GEANT simulations of a BA
F2 detector array. The position resolution results obtained by using t
his method are found to be substantially better than the first moment
method with logarithmic weighting.