Litcius/Paper detail

Introducing Probabilistic Bézier Curves for N-Step Sequence Prediction

Ronny Hug, Wolfgang Hübner, Michael Arens

2020Proceedings of the AAAI Conference on Artificial Intelligence11 citationsDOIOpen Access PDF

Abstract

Representations of sequential data are commonly based on the assumption that observed sequences are realizations of an unknown underlying stochastic process, where the learning problem includes determination of the model parameters. In this context, a model must be able to capture the multi-modal nature of the data, without blurring between single modes. This paper proposes probabilistic B'{e}zier curves (

Topics & Concepts

Probabilistic logicSequence (biology)Context (archaeology)Computer scienceBézier curveAlgorithmModalProcess (computing)MathematicsArtificial intelligenceGeometryPolymer chemistryBiologyPaleontologyChemistryGeneticsOperating systemImage and Signal Denoising MethodsMusic and Audio ProcessingNeural Networks and Applications