lecture14 (1)

lecture14 (1) - Historical Approaches in Machine Learning...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 14: Mercer's theorem, RKHS on Unbounded Domains, Frames Tomaso Poggio and Sayan Mukherjee Description We introduce an alternate perspective of RKHS via integral operators and Mercer's theorem. Formulate the problem of RKHS on unbounded domains. Construct RKHS from frames. Suggested Reading Rifkin. Everything Old Is New Again: A Fresh Look at
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Historical Approaches in Machine Learning. MIT Ph.D. Thesis, 2002. < • Evgeniou, Pontil and Poggio. Regularization Networks and Support Vector Machines Advances in Computational Mathematics, 2000. • V. N. Vapnik. The Nature of Statistical Learning Theory. Springer, 1995....
View Full Document

{[ snackBarMessage ]}

Ask a homework question - tutors are online