Kernels and RKHS
Speaker: Bülent Karasözen (Emeritus, Affiliated Faculty at the Institute of Applied Mathematics, METU)
Date / Time: Tuesday, March 5, 2024 / 15:40 (Ankara, Turkey)
Place: Online Participation (please self-register first, if necessary)
Abstract: In this talk, application kernels in machine learning are presented such as separating and detecting similarity between the objects. Construction and operation with kernels, such as the kernel trick and different types of kernels are introduced. A non-technical introduction to reproducing kernel Hilbert spaces (RKHSs) are given, and some basic algorithms in RHKS are described. Ridge regression as an application of the kernels is discussed.