B. NovaprateepK. KhompurngsonD. PoltemMahidol UniversityUniversity of Phayao2018-05-032018-05-032011-01-06International Journal of Mathematics and Computers in Simulation. Vol.5, No.1 (2011), 1-8199801592-s2.0-78650790484https://repository.li.mahidol.ac.th/handle/20.500.14594/11806In this paper, we briefly review Hypercircle inequality for data error (Hide) measured with square loss. We provide it in the case that the unit ball B is replaced by δB where δ is any positive number. Moreover, we also discuss some important facts of Hide for practical computation and study the problem in learning the value of a function in reproducing kernel Hilbert space (RKHS) by using the available material from Hide with different values of δ We compare our numerical experiment to the method of regularization, which is the standard method for learning problem.Mahidol UniversityComputer ScienceMathematicsArticleSCOPUS