Robust training of microwave neural network models using combined global/local optimization techniques

We present a new technique for training microwave neural network models. The proposed technique combines quasi-Newton algorithm with a recent global optimization algorithm called Particle Swarm Optimization (PSO). The quasi-Newton process for searching optimal solutions is incorporated into PSO to s...

Full description

Saved in:
Bibliographic Details
Published in2008 IEEE MTT-S International Microwave Symposium Digest pp. 995 - 998
Main Authors Hiroshi Ninomiya, Shan Wan, Kabir, Humayun, Xin Zhang, Zhang, Q.J.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2008
Subjects
Artificial neural networks
Global optimization
Microstrip filters
Microwave filters
Microwave theory and techniques
neural networks
particle swarm optimization
Solid modeling
Testing
Training
training algorithm
Online AccessGet full text

Cover

More Information
Summary:We present a new technique for training microwave neural network models. The proposed technique combines quasi-Newton algorithm with a recent global optimization algorithm called Particle Swarm Optimization (PSO). The quasi-Newton process for searching optimal solutions is incorporated into PSO to speed up local search, while the PSO performs global search avoid being trapped in local minima of training. The overall algorithm iterates between quasi-Newton and PSO. Neural network training for waveguide and microstrip examples are presented, demonstrating that the proposed algorithm achieves more accurate models than the conventional gradient based technique and the conventional PSO.
ISBN:1424417805
9781424417803
ISSN:0149-645X
2576-7216
DOI:10.1109/MWSYM.2008.4633002