Reconfigurable support vector machine classifier with approximate computing
Conferentiebijdragevan Leussen, M.J., Huisken, J., Wang, L., Jiao, H. & De Gyvez, J.P. (2017). Reconfigurable support vector machine classifier with approximate computing. Proceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017 (pp. 13-18). IEEE Computer Society. In Scopus Cited 0 times.
Support Vector Machine (SVM) is one of the most popular machine learning algorithms. An energy-efficient SVM classifier is proposed in this paper, where approximate computing is utilized to reduce energy consumption and silicon area. A hardware architecture with reconfigurable kernels and overflow-resilient limiter is presented. For different applications, different kernels can be chosen and configured to achieve the optimum energy efficiency while achieving the performance requirement. For an epileptic seizure detection application, on average, 15% energy and 14% area savings are achieved with the proposed approximate SVM classifier compared to a fully-accurate SVM implementation with almost no accuracy degradation.