FAST CURVE FITTING USING NEURAL NETWORKS
FAST CURVE FITTING USING NEURAL NETWORKS
复制标题
DOI：
10.1063/1.1143696
复制
发表时间：
1992-10-01
影响因子：
1.6
通讯作者：
ROACH, CM
中科院分区：
文献类型：
--
作者：
BISHOP, CM;ROACH, CM
神经网络为快速求解重复非线性曲线拟合问题提供了一种新的工具。在本文中，我们介绍了神经网络的概念，并展示了如何使用这种网络来拟合实验数据的函数形式。神经网络算法通常比传统的迭代方法快得多。此外，通过使用专用的网络硬件实现，可以进一步大幅提高速度，从而使该技术适用于快速实时应用。本文以核聚变研究中的一个简单例子说明了基本概念，该例子涉及到在COMPASS-C托卡马克中测量B IV杂质辐射的谱线参数的确定。
Neural networks provide a new tool for the fast solution of repetitive nonlinear curve fitting problems. In this article we introduce the concept of a neural network, and we show how such networks can be used for fitting functional forms to experimental data. The neural network algorithm is typically much faster than conventional iterative approaches. In addition, further substantial improvements in speed can be obtained by using special purpose hardware implementations of the network, thus making the technique suitable for use in fast real-time applications. The basic concepts are illustrated using a simple example from fusion research, involving the determination of spectral line parameters from measurements of B IV impurity radiation in the COMPASS-C tokamak.