01814nam 2200421z- 450 991058459200332120231214132819.01000146434(CKB)5580000000346214(oapen)https://directory.doabooks.org/handle/20.500.12854/90637(EXLCZ)99558000000034621420202208d2022 |y 0engurmn|---annantxtrdacontentcrdamediacrrdacarrierProbabilistic Parametric Curves for Sequence ModelingKarlsruheKIT Scientific Publishing20221 electronic resource (226 p.)Karlsruher Schriften zur Anthropomatik3-7315-1198-3 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.Maths for computer scientistsbicsscProbabilistische SequenzmodellierungStochastische ProzesseNeuronale NetzwerkeParametrische KurvenProbabilistic Sequence ModelingStochastic ProcessesNeural NetworksParametric CurvesMaths for computer scientistsHug Ronnyauth1323289BOOK9910584592003321Probabilistic Parametric Curves for Sequence Modeling3035450UNINA