Premium
Robust training of microwave neural models
Author(s) -
Devabhaktuni Vijay Kumar,
Xi Changgeng,
Wang Fang,
Zhang QiJun
Publication year - 2002
Publication title -
international journal of rf and microwave computer‐aided engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.335
H-Index - 39
eISSN - 1099-047X
pISSN - 1096-4290
DOI - 10.1002/mmce.10016
Subject(s) - artificial neural network , microwave , computer science , process (computing) , task (project management) , microwave engineering , macro , artificial intelligence , key (lock) , machine learning , engineering , systems engineering , telecommunications , computer security , programming language , operating system
Neural networks recently gained attention as a fast and flexible vehicle to microwave modeling and design. Neural network models can be developed by learning from microwave data, through a process called training. The trained models can be used during microwave design to provide instant answers to the task they learnt. This article addresses certain key challenges in developing RF/microwave neural models. An iterative multistage (IMS) approach including a macro‐level process and a stage‐level process is proposed. At the macro‐level, the IMS decomposes the complicated original task into several simpler subtasks or stages and at the stage‐level, the IMS utilizes a variety of neural network structures and effective training techniques, including several existing techniques and a new Huber quasi‐Newton (HQN) technique. The proposed HQN allows for the IMS approach to model only smooth portion of the problem behavior in one of the training stages, ignoring sharp/sudden variations. The advantages of the proposed microwave‐oriented modeling techniques are demonstrated through examples. © 2002 John Wiley & Sons, Inc. Int J RF and Microwave CAE 12: 109–124, 2002.