Derivation of kernel of dynamic support vector machines: Stochastic and deterministic data process
- Published
- Accepted
- Subject Areas
- Algorithms and Analysis of Algorithms, Data Mining and Machine Learning, Data Science
- Keywords
- DSVM, Stochastic Process, Deterministic Process, Information Geometry
- Copyright
- © 2016 Sato
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ PrePrints) and either DOI or URL of the article must be cited.
- Cite this article
- 2016. Derivation of kernel of dynamic support vector machines: Stochastic and deterministic data process. PeerJ PrePrints 4:e1624v1 https://doi.org/10.7287/peerj.preprints.1624v1
Abstract
We give an analytic derivation of kernel of dynamic support vector machine (DSVM). We show them for the cases of the data processes with stochastic and deterministic changes. We derive the kernels by solving Bellman equations. For the stochastic case, Gaussian kernel is naturally derived. For the deterministic case, the kernel is derived in the form of traveling wave. We also give comments from physical viewpoints in the context of information geometry. Physical comments include the equivalence principle in information geometric context and the relation to AdS/CFT correspondence.
Author Comment
This is a preprint submission to PeerJ Preprints. We give the derivations of kernel of DSVM for the data processes with stochastic and deterministic changes.