ENCYCLOPEDIA 4U .com

Encyclopedia Home Page

Mercer's theorem

Mercer's theorem is one of the most popular results of the work of James Mercer. It is used for the kernel trick, an important method in machine learning.

Mercer's theorem states that any positive definite kernel K(x, y) can be expressed as a dot product in a high-dimensional space.

More specifically, if a kernel is positive semi-definite, i.e.,

then there exists a function whose image is in an inner product space of possibly high dimension, such that

Content on this web site is provided for informational purposes only. We accept no responsibility for any loss, injury or inconvenience sustained by any person resulting from information published on this site. We encourage you to verify any critical information with the relevant authorities.

This article is licensed under the GNU Free Documentation License. It uses material from the Wikipedia article "Mercer's theorem".