Support vector machines for surrogate modeling of electronic circuits

In electronic circuit design, preliminary analyses of the circuit performances are generally carried out using time-consuming simulations. These analyses should be performed as fast as possible because of the strict temporal constraints on the industrial sector time to market. On the other hand, there is the need of precision and reliability of the analyses. For these reasons, there is more and more interest toward surrogate models able to approximate the behavior of a device with a high precision making use of a limited set of samples. Using suitable surrogate models instead of simulations, it is possible to perform a reliable analysis in less time. In this work, we are going to analyze how the surrogate models given by the support vector machine (SVM) perform when they are used to approximate the behavior of industrial circuits that will be employed in consumer electronics. The SVM is also compared to the surrogate models given by the response surface methodology using a commercial software currently adopted for this kind of applications.

[1]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[2]  T. Dhaene,et al.  RF circuit block modeling via Kriging surrogates , 2008, MIKON 2008 - 17th International Conference on Microwaves, Radar and Wireless Communications.

[3]  Piotr Breitkopf,et al.  Diffuse response surface model based on moving Latin hypercube patterns for reliability-based design optimization of ultrahigh strength steel NC milling parameters , 2011 .

[4]  Georges G. E. Gielen,et al.  Synthesis of Integrated Passive Components for High-Frequency RF ICs Based on Evolutionary Computation and Machine Learning Techniques , 2011, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[5]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[6]  Zhigang Zeng,et al.  Robust Passivity and Passification for a Class of Singularly Perturbed Nonlinear Systems with Time-Varying Delays and Polytopic Uncertainties via Neural Networks , 2013, Circuits Syst. Signal Process..

[7]  Dan Wang,et al.  Kriging Model combined with latin hypercube sampling for surrogate modeling of analog integrated circuit performance , 2009, 2009 10th International Symposium on Quality Electronic Design.

[8]  Zhigang Zeng,et al.  Associative Learning of Integrate-and-Fire Neurons with Memristor-Based Synapses , 2012, Neural Processing Letters.

[9]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[10]  F. Girosi,et al.  Nonlinear prediction of chaotic time series using support vector machines , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

[11]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.

[12]  J. Suykens.  Nonlinear modelling and support vector machines , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[13]  Dirk Gorissen,et al.  Sequential modeling of a low noise amplifier with neural networks and active learning , 2009, Neural Computing and Applications.

[14]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[15]  M. B. Steer,et al.  Surrogate-Model-Based Analysis of Analog Circuits—Part II: Reliability Analysis , 2011, IEEE Transactions on Device and Materials Reliability.

[17]  M. B. Steer,et al.  Surrogate-Model-Based Analysis of Analog Circuits—Part I: Variability Analysis , 2011, IEEE Transactions on Device and Materials Reliability.