Circuit analysis is an important phase of the circuit produc- tion process. This phase should be performed as fast as possible because of the strict temporal constraints in the industrial sector. On the other hand, there is the need of a certain precision and reliability of the anal- ysis. For this reasons there is more and more interest toward surrogate models that are able to perform a reliable analysis in less time. In this work we analyze how a popular surrogate model, the Support Vector Machines(SVM), performs when it is used to approximate the behavior of industrial circuits, provided by ST-Microelectronics, that will be em- ployed in consumer electronics. The SVM are also compared with the surrogate models created with the commercial software currently used by ST-Microelectronics for this kind of applications.
Circuit analysis is an important phase of the circuit production process. This phase should be performed as fast as possible because of the strict temporal constraints in the industrial sector. On the other hand, there is the need of a certain precision and reliability of the analysis. For this reasons there is more and more interest toward surrogate models that are able to perform a reliable analysis in less time. In this work we analyze how a popular surrogate model, the Support Vector Machines (SVM), performs when it is used to approximate the behavior of industrial circuits, provided by ST-Microelectronics, that will be employed in consumer electronics. The SVM are also compared with the surrogate models created with the commercial software currently used by ST-Microelectronics for this kind of applications. © Springer-Verlag Berlin Heidelberg 2013.
Support Vector Machines for Real Consumer Circuits / Angelo, Ciccazzo; DI PILLO, Gianni; Latorre, Vittorio. - 212:(2013), pp. 1199-1207. [10.1007/978-3-642-37502-6_140]
Support Vector Machines for Real Consumer Circuits
DI PILLO, Gianni;LATORRE, VITTORIO
2013
Abstract
Circuit analysis is an important phase of the circuit produc- tion process. This phase should be performed as fast as possible because of the strict temporal constraints in the industrial sector. On the other hand, there is the need of a certain precision and reliability of the anal- ysis. For this reasons there is more and more interest toward surrogate models that are able to perform a reliable analysis in less time. In this work we analyze how a popular surrogate model, the Support Vector Machines(SVM), performs when it is used to approximate the behavior of industrial circuits, provided by ST-Microelectronics, that will be em- ployed in consumer electronics. The SVM are also compared with the surrogate models created with the commercial software currently used by ST-Microelectronics for this kind of applications.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
