Probabilistic Parametric Curves for Sequence Modeling

By:

Hug, Ronny [auth]

Material type: Article

ArticleLanguage: English Series: Karlsruher Schriften zur AnthropomatikPublication details: Karlsruhe KIT Scientific Publishing 2022Description: 1 electronic resource (226 p.)ISBN:

9783731511984

Subject(s):

Online resources:

Summary: 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.

List(s) this item appears in: Faculty Informational Technology

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Collection	Shelving location	Call number	Status	Notes	Date due	Barcode
Electronic edition	Bucheon University Library	Computers	OAPEN	004 K21	Not for loan	View (pdf)		1010799

Open Access star Unrestricted online access

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.

Creative Commons by/4.0 cc

English

There are no comments on this title.

to post a comment.