Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386816076> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4386816076 endingPage "224" @default.
- W4386816076 startingPage "217" @default.
- W4386816076 abstract "One of the problems of machine learning is the criticality of algorithms for assessing the characteristics of input stochastic data to a priori uncertainty of their probability distributions. Machine learning theory is the most important area of artificial intelligence. One of the urgent problems of machine learning is to increase the accuracy and stability of the estimation of parameters of nonlinear stochastic processes handled in machine learning systems under conditions of uncertainty of their statistical characteristics. In this regard, the article considers an approach to solving the problem of robust (stable) stochastic filtration of a nonlinear stochastic process observed under conditions of interference with unknown probability distributions and generated by a stochastic nonlinear differential system. This system is perturbed by multiplicative noise with an unknown probability distribution from the class of distributions with bounded mean squares. The synthesis of the robust estimation of the considered nonlinear stochastic process was carried out on the basis of optimization of the developed criterion. This criterion is described by the sum of the integral quadratic form of the estimate and the nonlinear function of the measurement mismatch determined by the probabilistic distribution class of the measurement interference. The proposed algorithm uses a priori knowledge of the dynamic model of the stochastic process in contrast to the traditional approach to robust estimation. This makes it possible to increase the accuracy of the estimation without requiring knowledge of the type of distributions of object noise (generating differential system) and observer interference, unlike existing nonlinear filtering algorithms. At the same time, its implementation leads to significantly lower computational costs compared to both the traditional robust approach and modern non-linear filtering methods. The above advantages of the developed algorithm provide the possibility of its effective practical use when evaluating stochastic nonlinear processes handled in artificial intelligence systems in conditions of uncertainty, focused on application in a variety of technical systems - infocommunication, satellite navigation, avionics systems, etc." @default.
- W4386816076 created "2023-09-18" @default.
- W4386816076 creator A5023099756 @default.
- W4386816076 creator A5029479839 @default.
- W4386816076 creator A5091191809 @default.
- W4386816076 date "2023-01-01" @default.
- W4386816076 modified "2023-10-11" @default.
- W4386816076 title "Robust Filtering of Nonlinear Stochastic Processes in Machine Learning Systems" @default.
- W4386816076 cites W2080042467 @default.
- W4386816076 cites W2088853254 @default.
- W4386816076 cites W2095376999 @default.
- W4386816076 cites W2101084455 @default.
- W4386816076 cites W2162719021 @default.
- W4386816076 cites W2244328707 @default.
- W4386816076 cites W2910227445 @default.
- W4386816076 cites W2911755001 @default.
- W4386816076 cites W2937680865 @default.
- W4386816076 cites W2966088204 @default.
- W4386816076 cites W3091493936 @default.
- W4386816076 cites W3112358059 @default.
- W4386816076 cites W3113000041 @default.
- W4386816076 cites W3134449681 @default.
- W4386816076 cites W3163082599 @default.
- W4386816076 cites W3182867513 @default.
- W4386816076 cites W41409100 @default.
- W4386816076 cites W4205806204 @default.
- W4386816076 cites W4230624888 @default.
- W4386816076 cites W4319740376 @default.
- W4386816076 doi "https://doi.org/10.1007/978-3-031-43792-2_21" @default.
- W4386816076 hasPublicationYear "2023" @default.
- W4386816076 type Work @default.
- W4386816076 citedByCount "0" @default.
- W4386816076 crossrefType "book-chapter" @default.
- W4386816076 hasAuthorship W4386816076A5023099756 @default.
- W4386816076 hasAuthorship W4386816076A5029479839 @default.
- W4386816076 hasAuthorship W4386816076A5091191809 @default.
- W4386816076 hasConcept C105795698 @default.
- W4386816076 hasConcept C115961682 @default.
- W4386816076 hasConcept C121332964 @default.
- W4386816076 hasConcept C126255220 @default.
- W4386816076 hasConcept C149441793 @default.
- W4386816076 hasConcept C154945302 @default.
- W4386816076 hasConcept C158622935 @default.
- W4386816076 hasConcept C2775924081 @default.
- W4386816076 hasConcept C28826006 @default.
- W4386816076 hasConcept C33923547 @default.
- W4386816076 hasConcept C41008148 @default.
- W4386816076 hasConcept C47446073 @default.
- W4386816076 hasConcept C51955184 @default.
- W4386816076 hasConcept C62520636 @default.
- W4386816076 hasConcept C8272713 @default.
- W4386816076 hasConcept C99498987 @default.
- W4386816076 hasConceptScore W4386816076C105795698 @default.
- W4386816076 hasConceptScore W4386816076C115961682 @default.
- W4386816076 hasConceptScore W4386816076C121332964 @default.
- W4386816076 hasConceptScore W4386816076C126255220 @default.
- W4386816076 hasConceptScore W4386816076C149441793 @default.
- W4386816076 hasConceptScore W4386816076C154945302 @default.
- W4386816076 hasConceptScore W4386816076C158622935 @default.
- W4386816076 hasConceptScore W4386816076C2775924081 @default.
- W4386816076 hasConceptScore W4386816076C28826006 @default.
- W4386816076 hasConceptScore W4386816076C33923547 @default.
- W4386816076 hasConceptScore W4386816076C41008148 @default.
- W4386816076 hasConceptScore W4386816076C47446073 @default.
- W4386816076 hasConceptScore W4386816076C51955184 @default.
- W4386816076 hasConceptScore W4386816076C62520636 @default.
- W4386816076 hasConceptScore W4386816076C8272713 @default.
- W4386816076 hasConceptScore W4386816076C99498987 @default.
- W4386816076 hasLocation W43868160761 @default.
- W4386816076 hasOpenAccess W4386816076 @default.
- W4386816076 hasPrimaryLocation W43868160761 @default.
- W4386816076 hasRelatedWork W173174987 @default.
- W4386816076 hasRelatedWork W2022301265 @default.
- W4386816076 hasRelatedWork W2097880038 @default.
- W4386816076 hasRelatedWork W2115030441 @default.
- W4386816076 hasRelatedWork W2147578878 @default.
- W4386816076 hasRelatedWork W2159990075 @default.
- W4386816076 hasRelatedWork W2187808779 @default.
- W4386816076 hasRelatedWork W2216805223 @default.
- W4386816076 hasRelatedWork W2749437909 @default.
- W4386816076 hasRelatedWork W2799149877 @default.
- W4386816076 isParatext "false" @default.
- W4386816076 isRetracted "false" @default.
- W4386816076 workType "book-chapter" @default.