Ronny Hug

Probabilistic Parametric Curves for Sequence Modeling

Reihe:

Probabilistic Parametric Curves for Sequence Modeling
DOWNLOAD COVER

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.