top of page

Probabilistic Parametric Curves for Sequence Modeling

Inside this Book

If you make use of this material, you may credit the authors as follows:

Hug Ronny, "Probabilistic Parametric Curves for Sequence Modeling", KIT Scientific Publishing, 2022, DOI: 10.5445/KSP/1000146434, License:

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.


Probabilistische Sequenzmodellierung, Stochastische Prozesse, Neuronale Netzwerke, Parametrische Kurven, Probabilistic Sequence Modeling, Stochastic Processes, Neural Networks, Parametric Curves

Rights | License

Except where otherwise noted, this item has been published under the following license:

Takedown policy

If you believe that this publication infringes copyright, please contact us at and provide relevant details so that we can investigate your claim.

bottom of page