Pattern recognition in high energy physics with artificial neural networks — JETNET 2.0

Abstract A F77 package of adaptive artificial neural network algorithms, JETNET 2.0, is presented. Its primary target is the high energy physics community, but it is general enough to be used in any pattern-recognition application area. The basic ingredients are the multilayer perceptron back-propagation algorithm and the topological self-organizing map. The package consists of a set of subroutines, which can either be used with standard options or be easily modified to host alternative architectures ... Title of program: JETNET 2.0 Catalogue Id: ACGV_v1_0 Nature of problem High energy physics offers many challenging pattern recognition problems. It could be separating photons from leptons based on calorimeter information or the identification of a quark based on the kinematics of the hadronic fragmentation products. Standard procedures for such recognition problems is the introduction of relevant cuts in the multi-dimensional data. Versions of this program held in the CPC repository in Mendeley Data ACGV_v1_0; JETNET 2.0; 10.1016/0010-4655(92)90099-K ACGV_v2_0; JETNET VERSION 3.0; 10.1016/0010-4655(94)90120-1 This program has been imported from the CPC Program Library held at Queen's University Belfast (1969-2019)摘要 本文介绍了一款面向自适应人工神经网络算法的Fortran 77（F77）程序包JETNET 2.0。其核心服务群体为高能物理领域研究者，但因具备良好通用性，亦可应用于任意模式识别应用场景。该程序包的核心组件包括多层感知器反向传播（multilayer perceptron back-propagation）算法与拓扑自组织映射（topological self-organizing map）。本程序包由一系列子程序构成，既可以通过标准配置直接调用，也可轻松修改以适配其他架构…… 程序名称：JETNET 2.0 目录编号：ACGV_v1_0 问题特性 高能物理领域存在诸多极具挑战性的模式识别问题：例如基于量热仪数据区分光子与轻子，或根据强子碎裂产物的运动学特性识别夸克。针对这类识别任务的常规处理手段，是在多维数据中引入针对性的筛选截断条件。 孟德尔莱数据（Mendeley Data）中《Computer Physics Communications》（CPC）程序库收录的本程序版本： ACGV_v1_0；JETNET 2.0；DOI:10.1016/0010-4655(92)90099-K ACGV_v2_0；JETNET 3.0；DOI:10.1016/0010-4655(94)90120-1 本程序源自贝尔法斯特女王大学馆藏的CPC程序库（1969-2019）