Virtual Sensors for Semiconductor Manufacturing: A Nonparametric Approach - Exploiting Information Theoretic Learning and Kernel Machines
In this paper, a novel learning methodology is presented and discussed with reference to the application of virtual sensors in the semiconductor manufacturing environment. Density estimation techniques are used jointly with Renyi’s quadratic entropy to define a loss function for the learning problem, relying on Information Theoretic Learning concepts. Furthermore, Reproducing Kernel Hilbert Spaces (RKHS) theory is employed to handle nonlinearities and include regularization capabilities in the model. The proposed algorithm allows to estimate the structure of the predictive model, as well as the associated probabilistic uncertainty, in a nonparametric fashion. The methodology is then validated using simulation studies and process data from the semiconductor manufacturing industry. The proposed approach proves to be especially effective in strongly nongaussian environments and presents notable outlier filtering capabilities.
KeywordsSemiconductors Machine learning Entropy Kernel methods
Unable to display preview. Download preview PDF.
- 4.Gray, R.: Entropy and information theory. Springer (2010)Google Scholar
- 8.Popovic, D., Milosavljevic, V., Zekic, A., Macgearailt, N., Daniels, S.: Impact of low pressure plasma discharge on etch rate of SiO2 wafer. In: APS Meeting Abstracts, vol. 1, p. 8037P (2009)Google Scholar
- 9.Principe, J.: Information Theoretic Learning: Renyi’s Entropy and Kernel Perspectives. Springer (2010)Google Scholar
- 12.Scholkopf, B., Smola, A.: Learning with kernels, vol. 64. Citeseer (2002)Google Scholar
- 13.Silverman, B.: Density Estimation for Statistics and Data Analysis. Number 26 in Monographs on Statistics and Applied Probability (1986)Google Scholar
- 15.Weber, A.: Virtual metrology and your technology watch list: ten things you should know about this emerging technology. Future Fab International 22, 52–54 (2007)Google Scholar