Neural dipole localization by a hybrid nonlinear optimization algorithm

Proceedings. International Conference on Machine Learning and Cybernetics Pub Date : 2002-11-04 DOI:10.1109/ICMLC.2002.1167459

Sheng Ye, Jie Hu

引用次数: 0

Abstract

In the MEG inverse problem, the source localization procedure is to obtain dipole parameter solution that produces a calculated field pattern best matching the measured data. Here, a hybrid algorithm is described, i.e., Levenberg-Marquardt (LM) method for a fine scanning near the source area, and quasi-Newton (QN) method for a high-speed coarse scanning over a large area of the head. By a set of simulations, this presented algorithm can be more efficient both in computation time and sensitivity to the iterative initial value.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于混合非线性优化算法的神经偶极子定位

在磁相图反演问题中，源定位过程是获取偶极子参数解，使其产生与实测数据最匹配的计算场图。本文描述了一种混合算法，即在源区域附近进行精细扫描的Levenberg-Marquardt (LM)方法和在头部大面积范围内进行高速粗扫描的准牛顿(QN)方法。通过一组仿真，该算法在计算时间和对迭代初值的灵敏度上都具有较高的效率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Proceedings. International Conference on Machine Learning and Cybernetics

自引率

0.00%

发文量

期刊最新文献

Plenary Talk: Digital-Twin Fluid Engineering APPLYING MACHINE LEARNING TECHNIQUES IN DETECTING BACTERIAL VAGINOSIS. OPTICAL COHERENCE TOMOGRAPHY HEART TUBE IMAGE DENOISING BASED ON CONTOURLET TRANSFORM. The multistage support vector machine Anti-control of chaos based on fuzzy neural networks inverse system method