Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Bart van Erp"'
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 5, Pp 195-203 (2024)
Bayesian model reduction provides an efficient approach for comparing the performance of all nested sub-models of a model, without re-evaluating any of these sub-models. Until now, Bayesian model reduction has been applied mainly in the computational
Externí odkaz:
https://doaj.org/article/3bf40b51c4d14a3abb46257d6fa8a780
Publikováno v:
Entropy, Vol 25, Iss 8, p 1138 (2023)
Bayesian state and parameter estimation are automated effectively in a variety of probabilistic programming languages. The process of model comparison on the other hand, which still requires error-prone and time-consuming manual derivations, is often
Externí odkaz:
https://doaj.org/article/8cf056a91687485e98dcb229729ccc11
Publikováno v:
Frontiers in Robotics and AI, Vol 9 (2022)
The Free Energy Principle (FEP) postulates that biological agents perceive and interact with their environment in order to minimize a Variational Free Energy (VFE) with respect to a generative model of their environment. The inference of a policy (fu
Externí odkaz:
https://doaj.org/article/d70aa237da8a44e7bf8307eb51fa5541
Publikováno v:
Frontiers in Signal Processing, Vol 2 (2022)
In this paper we present Active Inference-Based Design Agent (AIDA), which is an active inference-based agent that iteratively designs a personalized audio processing algorithm through situated interactions with a human client. The target application
Externí odkaz:
https://doaj.org/article/db9a171255a542b1accfdca385ed1e9e
Publikováno v:
Applied Sciences, Vol 11, Iss 20, p 9535 (2021)
Effective noise reduction and speech enhancement algorithms have great potential to enhance lives of hearing aid users by restoring speech intelligibility. An open problem in today’s commercial hearing aids is how to take into account users’ pref
Externí odkaz:
https://doaj.org/article/0aba35f1109443db969c9df3427d4580
Publikováno v:
2022 IEEE Workshop on Signal Processing Systems (SiPS), 1-6
STARTPAGE=1;ENDPAGE=6;TITLE=2022 IEEE Workshop on Signal Processing Systems (SiPS)
STARTPAGE=1;ENDPAGE=6;TITLE=2022 IEEE Workshop on Signal Processing Systems (SiPS)
Model evidence is a fundamental performance measure in Bayesian machine learning as it represents how well a model fits an observed data set. Since model evidence is often an intractable quantity, the literature often resorts to computing instead the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::167c83096c19defe8e460384523cbc70
http://www.scopus.com/inward/record.url?scp=85141815712&partnerID=8YFLogxK
http://www.scopus.com/inward/record.url?scp=85141815712&partnerID=8YFLogxK
Publikováno v:
arXiv, 2022:2210.09134. Cornell University Library
Pure TUe
Pure TUe
Bayesian model reduction provides an efficient approach for comparing the performance of all nested sub-models of a model, without re-evaluating any of these sub-models. Until now, Bayesian model reduction has been applied mainly in the computational
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f850c9f4f498d1ff8629fb07b27b9141
https://arxiv.org/abs/2210.09134
https://arxiv.org/abs/2210.09134
Autor:
Bart van Erp, Bert de Vries
Publikováno v:
Proceedings of The 11th International Conference on Probabilistic Graphical Models, 186, 37-48
Pure TUe
Pure TUe
In this paper a modular approach to single-microphone source separation is proposed. A probabilistic model for mixtures of observations is constructed, where the independent underlying source signals are described by non-linear autoregressive models.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1d34f1a26e27314807586858e641ad72
https://research.tue.nl/nl/publications/904bf0bf-c391-4089-8587-875c819b64b4
https://research.tue.nl/nl/publications/904bf0bf-c391-4089-8587-875c819b64b4
Autor:
Bart van Erp, Bert de Vries
Publikováno v:
Pure TUe
30th European Signal Processing Conference, EUSIPCO 2022-Proceedings, 1397-1401
STARTPAGE=1397;ENDPAGE=1401;TITLE=30th European Signal Processing Conference, EUSIPCO 2022-Proceedings
30th European Signal Processing Conference, EUSIPCO 2022-Proceedings, 1397-1401
STARTPAGE=1397;ENDPAGE=1401;TITLE=30th European Signal Processing Conference, EUSIPCO 2022-Proceedings
This paper bridges the gap in the literature between neural networks and probabilistic graphical models. Invertible neural networks are incorporated in factor graphs and inference in this model is described by linearization of the network. Consequent
Publikováno v:
Software Impacts, 12:100299. Elsevier
Variational Bayesian (VB) inference has become an increasingly popular method for approximating exact Bayesian inference in model-based machine learning. The VB approach provides a way to trade off accuracy versus computational complexity and scales