Kannika KhompurngsonCharles A. MicchelliMahidol UniversityUniversity at Albany State University of New YorkCity University of Hong Kong2018-05-032018-05-032011-10-31Jaen Journal on Approximation. Vol.3, No.1 (2011), 87-11519897251188930662-s2.0-81855217448https://repository.li.mahidol.ac.th/handle/20.500.14594/12135In this paper we explore some aspects of the Hypercircle Inequality (Hi) in the context of kernel-based machine learning. We briefly describe Hi and its potential relevance to kernel- based learning when the data is known exactly and then extend it to circumstances where there is known data error (Hide). © 2011 Universidad de Jaén.Mahidol UniversityMathematicsArticleSCOPUS