Refine
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
Institute
- Physik (2)
Accurate impact parameter determination in a heavy-ion collision is crucial for almost all further analysis. We investigate the capabilities of an artificial neural network in that respect. First results show that the neural network is capable of improving the accuracy of the impact parameter determination based on observables such as the flow angle, the average directed inplane transverse momentum and the difference between transverse and longitudinal momenta. However, further investigations are necessary to discover the full potential of the neural network approach.
Abstract: An accurate impact parameter determination in a heavy ion collision is crucial for almost all further analysis. The capabilities of an artificial neural network are investigated to that respect. A novel input generation for the network is proposed, namely the transverse and longitudinal momentum distribution of all outgoing (or actually detectable) particles. The neural network approach yields an improvement in performance of a factor of two as compared to classical techniques. To achieve this improvement simple network architectures and a 5 × 5 input grid in (pt, pz) space are suffcient.
