Artificial neural networks may in some cases be alternatives to programmed computing. Since they offer a new important approach to information processing, we have investigated if the accuracy offered by this technique is good enough to extract physical information from the signals coming from a liquid argon time projection chamber. The results obtained implementing a neural network algorithm on a sequential scalar computer have been compared to those of a standard best-fit procedure on the same machine. This new method appears to be suited for the analysis of the events occurring in a very large detector, as that foreseen for the ICARUS experiment.
A NEURAL-NETWORK APPROACH FOR THE TPC SIGNAL-PROCESSING
CAVANNA, FLAVIO;
1995-01-01
Abstract
Artificial neural networks may in some cases be alternatives to programmed computing. Since they offer a new important approach to information processing, we have investigated if the accuracy offered by this technique is good enough to extract physical information from the signals coming from a liquid argon time projection chamber. The results obtained implementing a neural network algorithm on a sequential scalar computer have been compared to those of a standard best-fit procedure on the same machine. This new method appears to be suited for the analysis of the events occurring in a very large detector, as that foreseen for the ICARUS experiment.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
