9783731511984.pdf

9783731511984.pdf

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 advant...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Γλώσσα:English
Έκδοση: KIT Scientific Publishing 2022
Διαθέσιμο Online:https://doi.org/10.5445/KSP/1000146434
id oapen-20.500.12657-57539
record_format dspace
spelling oapen-20.500.12657-575392022-07-19T03:08:25Z Probabilistic Parametric Curves for Sequence Modeling Hug, Ronny Probabilistische Sequenzmodellierung Stochastische Prozesse Neuronale Netzwerke Parametrische Kurven Probabilistic Sequence Modeling Stochastic Processes Neural Networks Parametric Curves bic Book Industry Communication::U Computing & information technology::UY Computer science::UYA Mathematical theory of computation::UYAM Maths for computer scientists 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. 2022-07-18T11:55:27Z 2022-07-18T11:55:27Z 2022 book ONIX_20220718_9783731511984_116 1863-6489 9783731511984 https://library.oapen.org/handle/20.500.12657/57539 eng Karlsruher Schriften zur Anthropomatik application/pdf n/a 9783731511984.pdf https://doi.org/10.5445/KSP/1000146434 KIT Scientific Publishing KIT Scientific Publishing 10.5445/KSP/1000146434 10.5445/KSP/1000146434 44e29711-8d53-496b-85cc-3d10c9469be9 9783731511984 KIT Scientific Publishing 54 226 Karlsruhe open access
institution OAPEN
collection DSpace
language English
description 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.
title 9783731511984.pdf
spellingShingle 9783731511984.pdf
title_short 9783731511984.pdf
title_full 9783731511984.pdf
title_fullStr 9783731511984.pdf
title_full_unstemmed 9783731511984.pdf
title_sort 9783731511984.pdf
publisher KIT Scientific Publishing
publishDate 2022
url https://doi.org/10.5445/KSP/1000146434
_version_ 1771297564946071552

Παρόμοια τεκμήρια