High Energy Physics (HEP) experiments require discrimination of a few interesting events among a huge number of background events generated during an experiment. Hierarchical triggering hardware architectures are needed to perform this tasks in real-time. In this paper three neural network models are studied as possible candidate for such systems. A modified Multi-Layer Perception (MLP) architecture and a E alpha Net architecture are compared against a traditional MLP Test error below 25% is archived by all architectures in two different simulation strategies. E alpha Net performance are 1 to 2% better on test error with respect to the other two architectures using the smaller network topology. The design of a digital implementation of the proposed neural network is also outlined.
VITABILE S, G PILATO, G VASSALLO, SM SINISCALCHI, A GENTILE, F SORBELLO (2005). Neural Classification of HEP Experimental Data. In Biological and Artificial Intelligence Environments (pp.149-155). HEIDELBERG : Springer [10.1007/1-4020-3432-6_18].
Neural Classification of HEP Experimental Data
VITABILE, Salvatore;VASSALLO, Giorgio;SINISCALCHI, Sabato Marco;GENTILE, Antonio;SORBELLO, Filippo
2005-01-01
Abstract
High Energy Physics (HEP) experiments require discrimination of a few interesting events among a huge number of background events generated during an experiment. Hierarchical triggering hardware architectures are needed to perform this tasks in real-time. In this paper three neural network models are studied as possible candidate for such systems. A modified Multi-Layer Perception (MLP) architecture and a E alpha Net architecture are compared against a traditional MLP Test error below 25% is archived by all architectures in two different simulation strategies. E alpha Net performance are 1 to 2% better on test error with respect to the other two architectures using the smaller network topology. The design of a digital implementation of the proposed neural network is also outlined.File | Dimensione | Formato | |
---|---|---|---|
A10.100_F1-4020-3432-6_18.pdf
Solo gestori archvio
Dimensione
207.83 kB
Formato
Adobe PDF
|
207.83 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.