Robust training of microwave neural models

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.

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  Li Gao,et al.  Huber optimization of circuits: a robust approach , 1993 .

[3]  Fang Wang,et al.  Knowledge based neural models for microwave design , 1997, 1997 IEEE MTT-S International Microwave Symposium Digest.

[4]  Fang Wang,et al.  A hierarchical neural network approach to the development of library of neural models for microwave design , 1998, 1998 IEEE MTT-S International Microwave Symposium Digest (Cat. No.98CH36192).

[5]  M. Mongiardo,et al.  A neural network model for CAD and optimization of microwave filters , 1998, 1998 IEEE MTT-S International Microwave Symposium Digest (Cat. No.98CH36192).

[6]  T.W.S. Chow,et al.  Noise robustness enhancement using fourth-order cumulants cost function , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[7]  Emile Fiesler,et al.  High-order and multilayer perceptron initialization , 1997, IEEE Trans. Neural Networks.

[8]  Michel Nakhla,et al.  A neural network modeling approach to circuit optimization and statistical design , 1995 .

[9]  John W. Bandler,et al.  A nonlinear l_1 optimization algorithm for design, modeling, and diagnosis of networks , 1987 .

[10]  Kim Halskov,et al.  The Huber concept in device modeling, circuit diagnosis and design centering , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

[11]  A. R. Djordjević.  Matric parameters for multiconductor transmission lines : software and user's manual , 1989 .

[12]  Samuel Kaski,et al.  Dimensionality reduction by random mapping: fast similarity computation for clustering , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[13]  M. Vai,et al.  Automatic impedance matching with a neural network , 1993, IEEE Microwave and Guided Wave Letters.

[14]  Denis Barataud,et al.  Modeling microwave devices and circuits for telecommunications system design , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[15]  P.M. Watson,et al.  Development of knowledge based artificial neural network models for microwave components , 1998, 1998 IEEE MTT-S International Microwave Symposium Digest (Cat. No.98CH36192).

[16]  Ramesh C. Jain,et al.  A robust backpropagation learning algorithm for function approximation , 1994, IEEE Trans. Neural Networks.

[17]  G. L. Creech,et al.  Artificial neural networks for fast and accurate EM-CAD of microwave circuits , 1997 .

[18]  K. C. Gupta,et al.  EM-ANN models for microstrip vias and interconnects in dataset circuits , 1996 .

[19]  Q.J. Zhang,et al.  A Neural Network Approach to the Modeling of Heterojunction Bipolar Transistors from S-Parameter Data , 1998, 1998 28th European Microwave Conference.