JETNET 3.0—A versatile artificial neural network package

Abstract An F77 package for feed-forward artificial neural network data processing, JETNET 3.0, is presented. It represents a substantial extension and generalization of an earlier release, JETNET 2.0. The package, which consists of a set of subroutines, is focused on multilayer perceptron architectures. As compared to earlier versions it contains a variety of minimization options, measures for monitoring the learning process, limited precision emulation, etc. Also, the reader is provided with a set o... Title of program: JETNET VERSION 3.0 Catalogue Id: ACGV_v2_0 [ACTP] Nature of problem Challenging pattern recognition and non-linear modelling problems within high energy physics, ranging from off-line and on-line parton (or other constituent) identification tasks to accelerator beam control. Standard methods for such problems are typically confined to linear dependencies like Fischer discriminants, principal components analysis and ARMA models. 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 本文介绍了一款用于前馈人工神经网络（feed-forward artificial neural network）数据处理的F77软件包JETNET 3.0。该软件包是对早期发布版本JETNET 2.0的大幅扩展与泛化。此软件包由一系列子程序构成，专注于多层感知机（multilayer perceptron）架构。相较于早期版本，其新增了多种极小化选项、学习过程监控手段以及有限精度模拟等功能。此外，还为使用者提供了一系列…… 程序标题：JETNET 3.0版 目录编号：ACGV_v2_0 [ACTP] 问题类型 针对高能物理领域内的高难度模式识别与非线性建模问题，涵盖离线与在线的部分子（parton）识别任务，以及加速器束流控制任务。此类问题的传统解决方案通常仅能处理线性依赖关系，例如费希尔判别法（Fischer discriminants）、主成分分析（Principal Components Analysis）与自回归滑动平均（ARMA）模型。 存放在Mendeley数据的CPC库中的该程序版本包括： ACGV_v1_0；JETNET 2.0；10.1016/0010-4655(92)90099-K ACGV_v2_0；JETNET 3.0；10.1016/0010-4655(94)90120-1 本程序引自贝尔法斯特女王大学馆藏的CPC程序库（1969-2019）