LEADER 01814nam  2200421z- 450 
001 9910584592003321
005 20231214132819.0
010   $a1000146434
035   $a(CKB)5580000000346214
035   $a(oapen)https://directory.doabooks.org/handle/20.500.12854/90637
035   $a(EXLCZ)995580000000346214
100   $a20202208d2022      |y             0
101 0 $aeng
135   $aurmn|---annan
181   $ctxt$2rdacontent
182   $cc$2rdamedia
183   $acr$2rdacarrier
200 10$aProbabilistic Parametric Curves for Sequence Modeling
210   $aKarlsruhe$cKIT Scientific Publishing$d2022
215   $a1 electronic resource (226 p.)
225 1 $aKarlsruher Schriften zur Anthropomatik
311   $a3-7315-1198-3 
330   $aThis 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.
606   $aMaths for computer scientists$2bicssc
610   $aProbabilistische Sequenzmodellierung
610   $aStochastische Prozesse
610   $aNeuronale Netzwerke
610   $aParametrische Kurven
610   $aProbabilistic Sequence Modeling
610   $aStochastic Processes
610   $aNeural Networks
610   $aParametric Curves
615  7$aMaths for computer scientists
700   $aHug$b Ronny$4auth$01323289
906   $aBOOK
912   $a9910584592003321
996   $aProbabilistic Parametric Curves for Sequence Modeling$93035450
997   $aUNINA