arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1409.5244hep-phnucl-exnucl-th
收藏

神经网络在强子物理中的应用

Applications of Neural Networks in Hadron Physics

Krzysztof M. Graczyk, Cezary Juszczak

摘要:

回顾了前馈神经网络的贝叶斯方法。讨论了它在强子物理中的应用潜力。作为应用的一个例子,给出了双光子交换效应的研究。我们专注于模型的比较,由于模型的选择和过拟合的系统不确定性的估计。作为一个例子,给出了截面比$d σ(e^+ p\to e^+ p)/d σ(e^- p\to e^- p)$的预测以及由于参数化选择而引起的不确定性的估计。

英文摘要:

The Bayesian approach for the feed-forward neural networks is reviewed. Its potential for usage in hadron physics is discussed. As an example of the application the study of the the two-photon exchange effect is presented. We focus on the model comparison, the estimation of the systematic uncertainties due to the choice of the model, and the over-fitting. As an illustration the predictions of the cross sections ratio $d σ(e^+ p\to e^+ p)/d σ(e^- p\to e^- p)$ are given together with the estimate of the uncertainty due to the parametrization choice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑