TY - BOOK AU - Hug, Ronny PY - 2022 TI - Probabilistic Parametric Curves for Sequence Modeling AB - 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. Umfang: XII, 194 S. Preis: 44.00 € PB - KIT Scientific Publishing CY - Karlsruhe KW - Probabilistische Sequenzmodellierung KW - Stochastische Prozesse KW - Neuronale Netzwerke KW - Parametrische Kurven KW - Probabilistic Sequence Modeling KW - Stochastic Processes KW - Neural Networks KW - Parametric Curves SN - 978-3-7315-1198-4 DO - 10.5445/KSP/1000146434 SE - 226