FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2305518323> ?p ?o ?g. }

• W2305518323 abstract "Non-parametric Bayesian modelling offers a principled way for avoiding model selection such as pre-defining the number of modes in a mixture model or the optimal number of factors in factor analysis. Instead, Bayesian non-parametric methods allow the data to determine the complexity of model. In particular, the hierarchical Dirichlet process (HDP) is used in a variety of applications to infer an arbitrary number of classes from a set of samples. Within the temporal modelling paradigm, Bayesian non-parametrics is used to model sequential data by integrating HDP priors into state-space models such as HMM, constructing HDP-HMM. Also in latent factor modelling and dimensionality reduction, Indian buffet process (IBP) is a well-known method capable of sparse modelling and selecting an arbitrary number of factors among the often high-dimensional features.In this PhD thesis, we have applied the above methods to propose novel solutions to two prominent problems. The first model, named as ‘AdOn HDP-HMM’, is an adaptive online system based on HDP-HMM. ‘AdOn HDP-HMM’ is capable of segmenting and classifying the sequential data over unlimited number of classes, while meeting the memory and delay constraints of streaming contexts. The model is further enhanced by a number of learning rates, responsible for tuning the adaptability by determining the extent to which the model sustains its previous parameters or adapts to the new data. Empirical results on several variants of synthetic and action recognition data, show remarkable performance, particularly using adaptive learning rates for evolutionary sequences.The second proposed solution is an elaborate factor regression model, named as non-parametric conditional factor regression (NCFR), to cater for multivariate prediction, preserving the correlations in the response layer. NCFR enhances factor regression by integrating IBP to infer the optimal number of latent factors, in a sparse model. Thanks to this data-driven approach, NCFR can significantly avoid over-fitting even in cases where the ratio between the number of available samples and dimensions is very low. Experimental results on three diverse datasets give evidence of its remarkable predictive performance, resilience to over-fitting, good mixing and computational efficiency." @default.
• W2305518323 created "2016-06-24" @default.
• W2305518323 creator A5055525566 @default.
• W2305518323 date "2015-01-01" @default.
• W2305518323 modified "2023-09-27" @default.
• W2305518323 title "Bayesian non-parametric models for time segmentation and regression" @default.
• W2305518323 cites W2046866210 @default.
• W2305518323 cites W2078719085 @default.
• W2305518323 cites W2109434701 @default.
• W2305518323 hasPublicationYear "2015" @default.
• W2305518323 type Work @default.
• W2305518323 sameAs 2305518323 @default.
• W2305518323 citedByCount "0" @default.
• W2305518323 crossrefType "dissertation" @default.
• W2305518323 hasAuthorship W2305518323A5055525566 @default.
• W2305518323 hasConcept C105795698 @default.
• W2305518323 hasConcept C107673813 @default.
• W2305518323 hasConcept C111030470 @default.
• W2305518323 hasConcept C117251300 @default.
• W2305518323 hasConcept C119857082 @default.
• W2305518323 hasConcept C141318989 @default.
• W2305518323 hasConcept C153180895 @default.
• W2305518323 hasConcept C154945302 @default.
• W2305518323 hasConcept C171686336 @default.
• W2305518323 hasConcept C177769412 @default.
• W2305518323 hasConcept C23224414 @default.
• W2305518323 hasConcept C24574437 @default.
• W2305518323 hasConcept C2781280628 @default.
• W2305518323 hasConcept C33923547 @default.
• W2305518323 hasConcept C41008148 @default.
• W2305518323 hasConcept C500882744 @default.
• W2305518323 hasConcept C70518039 @default.
• W2305518323 hasConceptScore W2305518323C105795698 @default.
• W2305518323 hasConceptScore W2305518323C107673813 @default.
• W2305518323 hasConceptScore W2305518323C111030470 @default.
• W2305518323 hasConceptScore W2305518323C117251300 @default.
• W2305518323 hasConceptScore W2305518323C119857082 @default.
• W2305518323 hasConceptScore W2305518323C141318989 @default.
• W2305518323 hasConceptScore W2305518323C153180895 @default.
• W2305518323 hasConceptScore W2305518323C154945302 @default.
• W2305518323 hasConceptScore W2305518323C171686336 @default.
• W2305518323 hasConceptScore W2305518323C177769412 @default.
• W2305518323 hasConceptScore W2305518323C23224414 @default.
• W2305518323 hasConceptScore W2305518323C24574437 @default.
• W2305518323 hasConceptScore W2305518323C2781280628 @default.
• W2305518323 hasConceptScore W2305518323C33923547 @default.
• W2305518323 hasConceptScore W2305518323C41008148 @default.
• W2305518323 hasConceptScore W2305518323C500882744 @default.
• W2305518323 hasConceptScore W2305518323C70518039 @default.
• W2305518323 hasLocation W23055183231 @default.
• W2305518323 hasOpenAccess W2305518323 @default.
• W2305518323 hasPrimaryLocation W23055183231 @default.
• W2305518323 hasRelatedWork W1569016212 @default.
• W2305518323 hasRelatedWork W1849210333 @default.
• W2305518323 hasRelatedWork W2035923032 @default.
• W2305518323 hasRelatedWork W2084431760 @default.
• W2305518323 hasRelatedWork W2104552956 @default.
• W2305518323 hasRelatedWork W2258951259 @default.
• W2305518323 hasRelatedWork W2301058445 @default.
• W2305518323 hasRelatedWork W2311455220 @default.
• W2305518323 hasRelatedWork W2399786745 @default.
• W2305518323 hasRelatedWork W2613453453 @default.
• W2305518323 hasRelatedWork W2782586160 @default.
• W2305518323 hasRelatedWork W2796745763 @default.
• W2305518323 hasRelatedWork W2883670420 @default.
• W2305518323 hasRelatedWork W2890748370 @default.
• W2305518323 hasRelatedWork W2900157958 @default.
• W2305518323 hasRelatedWork W2963211851 @default.
• W2305518323 hasRelatedWork W2972860670 @default.
• W2305518323 hasRelatedWork W3086790268 @default.
• W2305518323 hasRelatedWork W3119803425 @default.
• W2305518323 hasRelatedWork W3183081247 @default.
• W2305518323 isParatext "false" @default.
• W2305518323 isRetracted "false" @default.
• W2305518323 magId "2305518323" @default.
• W2305518323 workType "dissertation" @default.