Neural Networks for Impact Parameter Determination
核理论
2008-11-26 v1
摘要
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 by 5 input grid in (p_t,p_z) space are sufficient.
引用
@article{arxiv.nucl-th/9601024,
title = {Neural Networks for Impact Parameter Determination},
author = {S. A. Bass and A. Bischoff and J. A. Maruhn and H. Stoecker and W. Greiner},
journal= {arXiv preprint arXiv:nucl-th/9601024},
year = {2008}
}
备注
Phys. Rev. C in print. Postscript-file also available at http://www.th.physik.uni-frankfurt.de/~bass/pub.html