In high energy particle colliders, detectors record millions of points of data during collision events. Therefore, good data analysis depends on distinguishing collisions which produce particles of interest (signal) from those producing other particles (background). Machine learning algorithms in the current times have become popular and useful as the method of choice for such large scale data analysis. In this work, we propose and implement an artificial neural network architecture to achieve the task of identifying precisely the parent particles from all the candidates arising out of track reconstruction from collision data in the future Compressed Baryonic Matter (CBM) experiment. Our framework performs comparably to the existing computational algorithm for this task even with a simple network architecture.

中文翻译：

---

用于识别煤层气实验中短寿命粒子的人工神经网络

在高能粒子对撞机中，探测器在碰撞事件期间记录数百万个数据点。因此，良好的数据分析取决于将产生感兴趣粒子（信号）的碰撞与产生其他粒子（背景）的碰撞区分开来。当前，机器学习算法已成为流行且有用的方法，可作为此类大规模数据分析的首选方法。在这项工作中，我们提出并实现了一种人工神经网络架构，以实现从未来压缩重子物质 (CBM) 实验中从碰撞数据中轨道重建产生的所有候选者中精确识别父粒子的任务。即使使用简单的网络架构，我们的框架也可以与现有的用于该任务的计算算法相媲美。