2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

IEEE Transactions on Microwave Theory and Techniques
Volume 48 Number 5, May 2000

Gradient Evaluation for Neural-Networks-Based Electromagnetic Optimization Procedures

Page 874.

Abstract:

This paper extends the use of a neural network (NN) approximating a function, to the evaluation of the gradient of the same function. This is done without any extra training of the network. The evaluation of the function's gradient is used in NN-based optimization procedures in order to speed up the convergence and to maintain the overall accuracy.

References

1. A. H. Zaabab, Q. Zhang and M. Nakhla, "A neural network modeling approach to circuit optimization and statistical design", IEEE Trans. Microwave Theory Tech., vol. 43, pp.  1349-1358, June  1995.
2. A. Veluswami, M. Nakhla and Q. Zhang, "The application of neural network to EM-based simulation and optimization of interconnects in high-speed VLSI circuits", IEEE Trans. Microwave Theory Tech., vol. 45, pp.  712 -722, May  1997.
3. J. W. Bandler, et al. "Electromagnetic optimization of 3-D structures", IEEE Trans. Microwave Theory Tech., vol. 45, pp.  770-779, May  1997.
4. M. Vai, S. Wu, B. Li and S. Prasad, "Reverse modeling of microwave circuits with bidirectional neural network models", IEEE Trans. Microwave Theory Tech., vol. 46, pp.  1492-1494, Oct.  1998.
5. C. R. Paul, Analysis of Multiconductor Transmission Lines, New York: Wiley, 1994.
6. W. H. Press, B. P. Flannery, S. A. Teukolsky and W. T. Vetterling, Numerical Recipes: The Art of Scientific Computing , Cambridge: U.K.: Cambridge Univ. Press, 1989.