\begin{document}$ 0 \leq b \leq 12.5 $\end{document} fm at \begin{document}$ \sqrt{s_{NN}} = 200 $\end{document} GeV are simulated using the AMPT model to provide preliminary final-state information. After transforming this information into appropriate input data (the energy spectra of final-state charged hadrons), we construct a multi-layer perceptron (MLP) and convolutional neural network (CNN) to connect final-state observables with the impact parameters. The results show that both the MLP and CNN can reconstruct the impact parameters with a mean absolute error approximately \begin{document}$ 0.4 $\end{document} fm, although the CNN behaves slightly better. Subsequently, we test the neural networks at different beam energies and pseudorapidity ranges in this task. These two models work well at both low and high energies. However, when conducting a test for a larger pseudorapidity window, the CNN exhibits a higher prediction accuracy than the MLP. Using the Grad-CAM method, we shed light on the 'attention' mechanism of the CNN model."> Determination of the impact parameter in high-energy heavy-ion collisions via deep learning -
  • [1]

    U. Heinz and R. Snellings, Annual Review of Nuclear and Particle Science63, 123 (2013)

  • [2]

    X.-G. Huang, Reports on Progress in Physics79, 076302 (2016)

  • [3]

    K. Hattori and X.-G. Huang, Nuclear Science and Techniques28, 26 (2017)

  • [4]

    C. Li, J. Zhou, and Y.-J. Zhou, Phys. Rev. D101, 034015 (2020)

  • [5]

    Y.-C. Liu and X.-G. Huang, Nuclear Science and Techniques31, 56 (2020)

  • [6]

    J.-H. Gao, G.-L. Ma, S. Puet al., Nuclear Science and Techniques31, 90 (2020)

  • [7]

    B. Abelev, J. Adam, D. Adamovaet al., Phys. Rev. C88, 044909 (2013)

  • [8]

    S. Balaban, inBiometric and Surveillance Technology for Human and Activity Identification XⅡ, Vol. 9457 (International Society for Optics and Photonics, 2015) p. 94570B

  • [9]

    C. David, M. Freslier, and J. Aichelin, Phys. Rev. C51, 1453 (1995)

  • [10]

    S. A. Bass, A. Bischoff, J. Maruhnet al., Phys. Rev. C53, 2358 (1996)

  • [11]

    F. Haddad, K. Hagel, J. Liet al., Phys. Rev. C55, 1371 (1997)

  • [12]

    F. Li, Y. Wang, H. Lüet al., Journal of Physics G: Nuclear and Particle Physics47, 115104 (2020)

  • [13]

    M. O. Kuttan, J. Steinheimer, K. Zhouet al., Phys. Lett. B811, 135872 (2020)

  • [14]

    F. Li, Y. Wang, Z. Gaoet al., Phys. Rev. C104, 034608 (2021)

  • [15]

    C. Y. Tsanget al., (2021), arXiv: 2107.13985[physics.ins-det]

  • [16]

    X. Zhanget al., (2021), arXiv: 2111.06597[nucl-th]

  • [17]

    N. Mallick, S. Tripathy, A. N. Mishraet al., Phys. Rev. D103, 094031 (2021)

  • [18]

    Z.-W. Lin, C. M. Ko, B.-A. Liet al., Phys. Rev. C72, 064901 (2005)

  • [19]

    C. Adam-Bourdarios, G. Cowan, C. Germainet al.,inNIPS 2014 Workshop on Highenergy Physics and Machine Learning(PMLR, 2015) pp. 19– 55

  • [20]

    K. Mills, M. Spanner, and I. Tamblyn, Phys. Rev. A96, 042113 (2017)

  • [21]

    G. Carleo and M. Troyer, Science355, 602 (2017)

  • [22]

    P. Baldi, P. Sadowski, and D. Whiteson, Nature communications5, 1 (2014)

  • [23]

    Y.-L. Du, K. Zhou, J. Steinheimeret al., European Physical Journal C80, 516 (2020)

  • [24]

    L.-G. Pang, K. Zhou, N. Suet al., Nature communications9, 1 (2018)

  • [25]

    R. Wang, Y.-G. Ma, R. Wadaet al., Physical Review Research2, 043202 (2020)

  • [26]

    H. Huang, B. Xiao, Z. Liuet al., Physical Review Research3, 023256 (2021)

  • [27]

    P. T. Komiske, E. M. Metodiev, and M. D. Schwartz, Journal of High Energy Physics2017, 1 (2017)

  • [28]

    Y.-L. Du, D. Pablos, and K. Tywoniuk, arXiv: 2106.11271 [hep-ph]

  • [29]

    Y.-S. Zhao, L. Wang, K. Zhouet al., arXiv: 2105.13761[hep-ph]

  • [30]

    J. He, W.-B. He, Y.-G. Maet al., Phys. Rev. C104, 044902 (2021)

  • [31]

    X.-N. Wang and M. Gyulassy, Phys. Rev. D44, 3501 (1991)

  • [32]

    B. Zhang, Computer Physics Communications.109, 193 (1998)

  • [33]

    B.-A. Li and C. M. Ko, Phys. Rev. C52, 2037 (1995)

  • [34]

    Z. Qiu and U. Heinz, Phys. Rev. C84, 024911 (2011)

  • [35]

    I. Bearden, D. Beavis, C. Besliuet al., Phys. Rev. Lett.88, 202301 (2002)

  • [36]

    P. Sarin,Measurement of charged particle multiplicity distribution in Au+ Au collisions up to 200 GeV, Ph.D. thesis, Massachusetts Institute of Technology (2003)

  • [37]

    X. Luo and N. Xu, Nuclear Science and Techniques28, 112 (2017)

  • [38]

    M. L. Miller, K. Reygers, S. J. Sanderset al., Annual Review of Nuclear and Particle Science57, 205 (2007)

  • [39]

    Y. Bathaee, Harvard Journal of Law & Technology31, 889 (2017)

  • [40]

    N. Tishby and N. Zaslavsky, in2015 IEEE Information Theory Workshop (ITW)(IEEE, 2015) pp. 1–5

  • [41]

    R. Shwartz-Ziv and N. Tishby, arXiv: 1703.00810[cs.LG]

  • [42]

    B. Zhou, A. Khosla, A. Lapedrizaet al., inProceedings of the IEEE conference on computer vision and pattern recognition(2016) pp. 2921–2929

  • [43]

    R. R. Selvaraju, M. Cogswell, A. Daset al., inProceedings of the IEEE international conference on computer vision(2017) pp. 618–626

Baidu
map