Title :
New iterative inverse scattering algorithms based on neural networks
Author :
Lee, Hyuek-Jae ; Ahn, Chang-Hoi ; Park, Cheon-Seok ; Jeong, Bong-Sik ; Lee, Soo-Young
Author_Institution :
GoldStar Central Res. Lab., Seoul, South Korea
fDate :
9/1/1994 12:00:00 AM
Abstract :
By introducing analogy between electromagnetic field problems and neural network models, new iterative numerical methods are developed for inverse scattering problems. Both recurrent and feedforward neural network architectures are developed, and the validity of the proposed algorithms is demonstrated by computer simulation for small dielectric cylinders
Keywords :
digital simulation; electrical engineering computing; electromagnetic fields; electromagnetic wave scattering; feedforward neural nets; inverse problems; iterative methods; recurrent neural nets; electromagnetic field problems; feedforward neural network; inverse scattering algorithms; iterative numerical methods; neural networks; recurrent neural network; small dielectric cylinders; Computer architecture; Electromagnetic fields; Electromagnetic modeling; Feedforward neural networks; Inverse problems; Iterative algorithms; Iterative methods; Neural networks; Numerical models; Recurrent neural networks;
Journal_Title :
Magnetics, IEEE Transactions on
