
- Hug, Ronny
Probabilistic Parametric Curves for Sequence Modeling
- Kartoniert,
- KIT Scientific Publishing
- (2022)
This work proposes a probabilistic extension to Bézier curves as a basis for effectively modeling stochastic processes with a bounded index set. The proposed stochastic process model is based on Mixture Density Networks and Bézier curves with Gaussian random variables as control points. A key advantage of this model is given by the ability to generate multi-mode predictions in a single inference step, thus avoiding the need for Monte Carlo simulation.
DETAILS
- Probabilistic Parametric Curves for Sequence Modeling
- Hug, Ronny
- Kartoniert, 226 S.
- graph. Darst.
- Sprache: Englisch
- 210 mm
- ISBN-13: 978-3-7315-1198-4
- Titelnr.: 96026407
- Gewicht: 430 g
- KIT Scientific Publishing (2022)
Herstelleradresse
KIT Scientific Publishing
Strasse am Forum 2
76131 - DE Karlsruhe
E-Mail: info@ksp.kit.edu