Classifying circuit performance using active-learning guided support vector machines

Authors:
Honghuang Lin;Peng Li
Affiliations:
Texas A&M University, College Station, TX;Texas A&M University, College Station, TX
Venue:
Proceedings of the International Conference on Computer-Aided Design
Year:
2012

Citing 10
Cited 1

Support-Vector Networks

Machine Learning
Support vector machines, reproducing kernel Hilbert spaces, and randomized GACV

Advances in kernel methods
Remembrance of circuits past: macromodeling by data mining in large analog design spaces

Proceedings of the 39th annual Design Automation Conference
Support vector machines for analog circuit performance representation

Proceedings of the 40th annual Design Automation Conference
Support vector machine active learning with applications to text classification

The Journal of Machine Learning Research
Mixture importance sampling and its application to the analysis of SRAM designs in the presence of rare failure events

Proceedings of the 43rd annual Design Automation Conference
Considering Cost Asymmetry in Learning Classifiers

The Journal of Machine Learning Research
Statistical diagnosis of unmodeled systematic timing effects

Proceedings of the 45th annual Design Automation Conference
Statistical blockade: very fast statistical simulation and modeling of rare circuit events and its application to memory design

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Efficient SRAM failure rate prediction via Gibbs sampling

Proceedings of the 48th Design Automation Conference

Verification of digitally-intensive analog circuits via kernel ridge regression and hybrid reachability analysis

Proceedings of the 50th Annual Design Automation Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

Leveraging machine learning has been proven as a promising avenue for addressing many practical circuit design and verification challenges. We demonstrate a novel active learning guided machine learning approach for characterizing circuit performance. When employed under the context of support vector machines, the proposed probabilistically weighted active learning approach is able to dramatically reduce the size of the training data, leading to significant reduction of the overall training cost. The proposed active learning approach is extended to the training of asymmetric support vector machine classifiers, which is further sped up by a global acceleration scheme. We demonstrate the excellent performance of the proposed techniques using three case studies: PLL lock-time verification, SRAM yield analysis and prediction of chip peak temperature using a limited number of on-chip temperature sensors.