Abstract
The use of global surrogate models has become commonplace as a cost effective alternative for performing complex high fidelity computer simulations. Due to their compact formulation and negligible evaluation time, global surrogate models are very useful tools for exploring the design space, what-if analysis, optimization, prototyping, visualization, and sensitivity analysis. Neural networks have been proven particularly useful in this respect due to their ability to model high dimensional, non-linear responses accurately. In this article, we present the results of an extensive study on the performance of neural networks as compared to other modeling techniques in the context of active learning. We investigate the scalability and accuracy in function of the number design variables and number of datapoints. The case study under consideration is a high dimensional, parametrized low noise amplifier RF circuit block.
Similar content being viewed by others
References
Anastasiadis D, Magoulas D (2006) Analysing the localisation sites of proteins through neural networks ensembles. Neural Comput Appl 15(3):277–288. doi:10.1007/s00521-006-0029-y
Busby D, Farmer CL, Iske A (2007) Hierarchical nonlinear approximation for experimental design and statistical data fitting. SIAM J Sci Comput 29(1):49–69. doi:10.1137/050639983
Chen J, Adams BJ (2006) Integration of artificial neural networks with conceptual models in rainfall-runoff modeling. J Hydrol 318:232–249
Clarke SM, Griebsch JH, Simpson TW (2003) Analysis of support vector regression for approximation of complex engineering analyses. In: Proceedings of the 29th design automation conference (ASME Design Engineering Technical Conferences) (DAC/DETC’03)
Crombecq K (2007) A gradient based approach to adaptive metamodeling. Tech. rep., University of Antwerp
Devabhaktuni V, Chattaraj B, Yagoub M, Zhang QJ (2003) Advanced microwave modeling framework exploiting automatic model generation, knowledge neural networks, and space mapping. IEEE Trans Microw Theory Tech 51(7):1822–1833. doi:10.1109/TMTT.2003.814318
Devabhaktuni V, Yagoub M, Fang Y, Xu J, Zhang Q (2001) Neural networks for microwave modeling: model development issues and nonlinear modeling techniques. Int J RF Microw CAE 11:4–21
Foresee F, Hagan M (1997) Gauss-newton approximation to bayesian regularization. In: Proceedings of the 1997 international joint conference on neural networks, pp 1930–1935
Ganser M, Grossenbacher K, Schutz M, Willmes L, Back T (2007) Simulation meta-models in the early phases of the product development process. In: Proceedings of efficient methods for robust design and optimization (EUROMECH 07)
Gorissen D (2007) Heterogeneous evolution of surrogate models. Master’s thesis, Master of AI, Katholieke Universiteit Leuven (KUL)
Gorissen D, Hendrickx W, Crombecq K, Dhaene T (2007) Adaptive distributed metamodeling. In: Dayde M et al (eds) Proceedings of 7th international meeting on high performance computing for computational science (VECPAR 2006). Lecture notes in computer science, vol 4395. Springer, Hiedelberg, pp 579–588
Gorissen D, De Tommasi L, Croon J, Dhaene T (2008) Automatic model type selection with heterogeneous evolution: an application to rf circuit block modeling. In: Proceedings of the IEEE congress on evolutionary computation, WCCI 2008, Hong Kong
Gorissen D, De Tommasi L, Hendrickx W, Croon J, Dhaene T (2008) Rf circuit block modeling via kriging surrogates. In: Proceedings of the 17th international conference on microwaves, radar and wireless communications (MIKON 2008)
Hendrickx W, Gorissen D, Dhaene T (2006) Grid enabled sequential design and adaptive metamodeling. In: WSC ’06: Proceedings of the 37th conference on winter simulation. Winter Simulation Conference, pp 872–881
Lophaven SN, Nielsen HB, Søndergaard J (2002) Aspects of the matlab toolbox DACE. Tech. rep., Informatics and Mathematical Modelling, Technical University of Denmark, DTU, Richard Petersens Plads, Building 321, DK-2800 Kgs. Lyngby
MacKay DJC (1992) Bayesian model comparison and backprop nets. In: Moody JE, Hanson SJ, Lippmann RP (eds) Advances in neural information processing systems 4. Morgan Kaufmann, San Mateo, pp 839–846
Pao HT, Chih YY (2006) Comparison of tscs regression and neural network models for panel data forecasting: debt policy. Neural Comput Appl 15(2):117–123. doi:10.1007/s00521-005-0014-x
Rasmussen CE, Williams CKI (2006) Gaussian processes for machine learning. MIT Press, Cambridge
Suykens J, Gestel TV, Brabanter JD, Moor BD, Vandewalle J (2002) Least squares support vector machines. World Scientific Publishing Co., Pte, Ltd., Singapore
Ye K, Li W, Sudjianto A (2000) Algorithmic construction of optimal symmetric latin hypercube designs. J Stat Plan Inference 90:145–159
Zhang Q, Gupta K, Devabhaktuni V (2003) Artificial neural networks for RF and microwave design: from theory to practice. IEEE Trans Microw Theory Tech 51:1339–1350
Zhang QJ, Gupta KC (2000) Neural networks for RF and microwave design (Book + Neuromodeler Disk). Artech House, Inc., Norwood
Acknowledgments
The authors would like to thank Jeroen Croon from the NXP-TSMC Research Center, Device Modeling Department, Eindhoven, The Netherlands for the LNA simulation code and Joost Rommes from Corporate I&T/Design Technology & Flows, NXP Semiconductors, Eindhoven for the many fruitful discussions. This work was supported by FWO Flanders, the Science and Innovation Administration Flanders, and the O-MOORE-NICE! project as supported by the European Commission through the Marie Curie program under contract number MTKI-CT-2006-042477.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gorissen, D., De Tommasi, L., Crombecq, K. et al. Sequential modeling of a low noise amplifier with neural networks and active learning. Neural Comput & Applic 18, 485–494 (2009). https://doi.org/10.1007/s00521-008-0223-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-008-0223-1