Probabilistic Parametric Curves for Sequence Modeling

• Autore: Hug Ronny
• Pubblicazione: Karlsruhe, : KIT Scientific Publishing, 2022
• Descrizione fisica: 1 electronic resource (226 p.)
• Soggetto topico: Maths for computer scientists
• Soggetto non controllato: Probabilistische Sequenzmodellierung; Stochastische Prozesse; Neuronale Netzwerke; Parametrische Kurven; Probabilistic Sequence Modeling; Stochastic Processes; Neural Networks; Parametric Curves
• Sommario/riassunto: 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.
• Titolo autorizzato: Probabilistic Parametric Curves for Sequence Modeling
• ISBN: 1000146434
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910584592003321
• Lo trovi qui: Univ. Federico II