S
Sebastian Mika
Researcher at Technical University of Berlin
Publications - 36
Citations - 12069
Sebastian Mika is an academic researcher from Technical University of Berlin. The author has contributed to research in topics: Support vector machine & Kernel method. The author has an hindex of 26, co-authored 36 publications receiving 11624 citations. Previous affiliations of Sebastian Mika include Boehringer Ingelheim & University of Potsdam.
Papers
More filters
Journal ArticleDOI
An introduction to kernel-based learning algorithms
TL;DR: This paper provides an introduction to support vector machines, kernel Fisher discriminant analysis, and kernel principal component analysis, as examples for successful kernel-based learning methods.
Proceedings ArticleDOI
Fisher discriminant analysis with kernels
TL;DR: In this article, a non-linear classification technique based on Fisher's discriminant is proposed and the main ingredient is the kernel trick which allows the efficient computation of Fisher discriminant in feature space.
Journal ArticleDOI
Input space versus feature space in kernel-based methods
Bernhard Schölkopf,Sebastian Mika,C.J.C. Burges,P. Knirsch,Klaus-Robert Müller,Gunnar Rätsch,Alexander J. Smola +6 more
TL;DR: The geometry of feature space is reviewed, and the connection between feature space and input space is discussed by dealing with the question of how one can, given some vector in feature space, find a preimage in input space.
Proceedings Article
Kernel PCA and De-Noising in Feature Spaces
Sebastian Mika,Bernhard Schölkopf,Alexander J. Smola,Klaus-Robert Müller,Matthias Scholz,Gunnar Rätsch +5 more
TL;DR: This work presents ideas for finding approximate pre-images, focusing on Gaussian kernels, and shows experimental results using these pre- images in data reconstruction and de-noising on toy examples as well as on real world data.
Proceedings ArticleDOI
A kernel view of the dimensionality reduction of manifolds
TL;DR: Isomap, graph Laplacian eigenmap, and locally linear embedding all utilize local neighborhood information to construct a global embedding of the manifold and it is shown how all three algorithms can be described as kernel PCA on specially constructed Gram matrices.