An active learning scheme using support vector machines for analog circuit feasibility classification

Ding, Mengmeng; Vemur, R.I.

doi:10.1109/icvd.2005.47

Cited by 18 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Section 3 gives a brief overview of SVM classifier and regressor. In Section 4, we give a brief overview of the active learning scheme [5] for feasibility modeling. Section 5 shows the experimental results of the proposed methodology.…”

Section: 3mentioning

confidence: 99%

“…We thus define a feasibility function y (X) whose output only takes two values {+1, −1} depending on whether X ∈ I [5].…”

Section: Feasibility Design Spacementioning

confidence: 99%

“…The performance models are defined and valid in the feasible design space. In contrast to [14], feasible design space identification problem is treated as a two class classification problem and an active learning scheme [5] using Support Vector Machines (SVMs) is used to tackle the sparsity of the feasible designs. Experimental results will show that our feasibility model has an overall accuracy of 99%.…”

Section: 3mentioning

confidence: 99%

“…The generalized optimal hyperplane is constructed by solving the optimization problem in Equation 5.…”

Section: Svm Classifiermentioning

confidence: 99%

“…Feasibility macromodeling is formulated as a classification problem while performance macromeling as a regression problem. An active learning scheme [5] has been applied to improve the accuracy of the feasibility model much faster than only using uniformly distributed designs in the entire design space. Our experiment shows that the performance macromodels in the feasible design space are more accurate and faster to construct and evaluate than performance macromodels in the entire design space without functional or performance constraints considered.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A combined feasibility and performance macromodel for analog circuits

Ding

Vemuri

2005

Proceedings of the 42nd Annual Conference on Design Automation - DAC '05

View full text Add to dashboard Cite

The need to reuse the performance macromodels of an analog circuit topology challenges existing regression based modeling techniques. A model of good reusability should have a number of independent design parameters and each parameter can vary in a large numeric range. On the other hand, these requirements can cause a large percentage of functionally incorrect designs in the design space and thus results in a sparse feasible design space. They also complicate the mathematical relationship between the performance parameters and the design parameters. In order to tackle these challenges, this paper presents a combined feasibility and performance macromodel based on Support Vector Machines (SVMs). The feasibility model identifies the feasible designs that satisfy the design constraints. The performance macromodel is valid for feasible designs. Feasibility macromodeling is formulated as a classification problem while performance macromeling as a regression problem. An active learning scheme [5] has been applied to improve the accuracy of the feasibility model much faster than only using uniformly distributed designs in the entire design space. Our experiment shows that the performance macromodels in the feasible design space are more accurate and faster to construct and evaluate than performance macromodels in the entire design space without functional or performance constraints considered.

show abstract

Section: 3mentioning

confidence: 99%

“…We thus define a feasibility function y (X) whose output only takes two values {+1, −1} depending on whether X ∈ I [5].…”

Section: Feasibility Design Spacementioning

confidence: 99%

Section: 3mentioning

confidence: 99%

“…The generalized optimal hyperplane is constructed by solving the optimization problem in Equation 5.…”

Section: Svm Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A combined feasibility and performance macromodel for analog circuits

Ding

Vemuri

2005

Proceedings of the 42nd Annual Conference on Design Automation - DAC '05

View full text Add to dashboard Cite

show abstract

Recent advances in space‐mapping‐based modeling of microwave devices

Koziel

2010

Int J Numerical Modelling

View full text Add to dashboard Cite

SUMMARYWe review the latest developments in space-mapping-based modeling techniques with applications in microwave engineering. We discuss the two techniques that utilize a combination of standard space mapping and function approximation methodologies, in particular fuzzy systems and support vector regression (SVR). In both cases, the initial space-mapping model is enhanced by an additional term that approximates the differences between the fine model and the initial space-mapping surrogate. We compare the standard and enhanced space-mapping models, as well as the fuzzy systems and SVR directly used for modeling fine model data. A discussion of the advantages and disadvantages of the presented methods is also given.

show abstract

Automatic Approximation of Expensive Functions with Active Learning

Gorissen

Crombecq

Couckuyt

et al. 2009

Studies in Computational Intelligence

View full text Add to dashboard Cite

Abstract. The use of computer simulations has become a viable alternative for real-life controlled experiments. Due to the computational cost of these high fidelity simulations, surrogate models are often employed as an approximation for the original simulator. Because of their compact formulation and negligible evaluation time, global surrogate models are very useful tools for exploring the design space, optimization, visualization and sensitivity analysis. Additionally, multiple surrogate models can be chained together to model large scale systems where the direct use of the original expensive simulators would be too cumbersome. Many surrogate model types, such as neural networks, support vector machines and rational models have been proposed, and many more techniques have been developed to minimize the number of expensive simulations required to train a sufficiently accurate surrogate model. In this chapter, we present a fully automated and integrated global surrogate modeling methodology for regression modeling and active learning that readily enables the adoption of advanced global surrogate modeling methods by application scientists. The work brings together insights from distributed systems, artificial intelligence, and modeling & simulation, and has applications in a very wide range of fields. The merits of this approach are illustrated with several examples, and several surrogate model types.

show abstract

An active learning scheme using support vector machines for analog circuit feasibility classification

Cited by 18 publications

References 15 publications

A combined feasibility and performance macromodel for analog circuits

A combined feasibility and performance macromodel for analog circuits

Recent advances in space‐mapping‐based modeling of microwave devices

Automatic Approximation of Expensive Functions with Active Learning

Contact Info

Product

Resources

About