NEW ITERATIVE INVERSE SCATTERING ALGORITHMS BASED ON NEURAL NETWORKS

被引：5

作者：

LEE, HJ

AHN, CH

PARK, CS

JEONG, BS

LEE, SY

机构：

[1] YEUNGNAM UNIV, DEPT ELECT ENGN, KYUNGBUK 712749, SOUTH KOREA

[2] KOREA ADV INST SCI & TECHNOL, DEPT ELECT ENGN, TAEJON 305701, SOUTH KOREA

来源：

IEEE TRANSACTIONS ON MAGNETICS | 1994年 / 30卷 / 05期

关键词：

D O I：

10.1109/20.312729

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

By introducing analogy between electromagnetic field problems and neural network models, new iterative numerical methods are developed for inverse scattering problems. Both recurrent and feedfoward neural network architectures are developed, and the validity of the proposed algorithms is demonstrated by computer simulation for small dielectric cylinders.

引用

页码：3641 / 3643

页数：3

共 9 条

[1] NONPERTURBATIVE DIFFRACTION TOMOGRAPHY VIA GAUSS-NEWTON ITERATION APPLIED TO THE SCATTERING INTEGRAL-EQUATION [J].