Zobrazeno 1 - 10
of 949
pro vyhledávání: '"de Vries, Bert"'
Autor:
van Erp, Bart, de Vries, Bert
This paper proposes improvements over earlier work by Nazareth and Blei (2022) for estimating the depth of Bayesian neural networks. Here, we propose a discrete truncated normal distribution over the network depth to independently learn its mean and
Externí odkaz:
http://arxiv.org/abs/2410.10395
Autor:
Nuijten, Wouter W. L., de Vries, Bert
Active Inference is a framework that emphasizes the interaction between agents and their environment. While the framework has seen significant advancements in the development of agents, the environmental models are often borrowed from reinforcement l
Externí odkaz:
http://arxiv.org/abs/2409.11087
Autor:
de Vries, Bert
The theoretical properties of active inference agents are impressive, but how do we realize effective agents in working hardware and software on edge devices? This is an interesting problem because the computational load for policy exploration explod
Externí odkaz:
http://arxiv.org/abs/2307.14145
The Free Energy Principle (FEP) is a theoretical framework for describing how (intelligent) systems self-organise into coherent, stable structures by minimising a free energy functional. Active Inference (AIF) is a corollary of the FEP that specifica
Externí odkaz:
http://arxiv.org/abs/2306.08014
Publikováno v:
Entropy. 2023; 25(8):1138
Bayesian state and parameter estimation have been 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
Externí odkaz:
http://arxiv.org/abs/2306.05965
The Free Energy Principle (FEP) describes (biological) agents as minimising a variational Free Energy (FE) with respect to a generative model of their environment. Active Inference (AIF) is a corollary of the FEP that describes how agents explore and
Externí odkaz:
http://arxiv.org/abs/2306.02733
Publikováno v:
IEEE Open Journal of Signal Processing 5 (2023) 195-203
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:
http://arxiv.org/abs/2210.09134
Autor:
van der Laan, Liselot, Silva, Ananília, Kleinendorst, Lotte, Rooney, Kathleen, Haghshenas, Sadegheh, Lauffer, Peter, Alanay, Yasemin, Bhai, Pratibha, Brusco, Alfredo, de Munnik, Sonja, de Vries, Bert B.A., Vega, Angelica Delgado, Engelen, Marc, Herkert, Johanna C., Hochstenbach, Ron, Hopman, Saskia, Kant, Sarina G., Kira, Ryutaro, Kato, Mitsuhiro, Keren, Boris, Kroes, Hester Y., Levy, Michael A., Lock-Hock, Ngu, Maas, Saskia M., Mancini, Grazia M.S., Marcelis, Carlo, Matsumoto, Naomichi, Mizuguchi, Takeshi, Mussa, Alessandro, Mignot, Cyril, Närhi, Anu, Nordgren, Ann, Pfundt, Rolph, Polstra, Abeltje M., Trajkova, Slavica, van Bever, Yolande, José van den Boogaard, Marie, van der Smagt, Jasper J., Barakat, Tahsin Stefan, Alders, Mariëlle, Mannens, Marcel M.A.M., Sadikovic, Bekim, van Haelst, Mieke M., Henneman, Peter
Publikováno v:
In Human Genetics and Genomics Advances 9 January 2025 6(1)
Autor:
van der Sluijs, Pleuntje J., Moutton, Sébastien, Dingemans, Alexander J.M., Weis, Denisa, Levy, Michael A., Boycott, Kym M., Arberas, Claudia, Baldassarri, Margherita, Beneteau, Claire, Brusco, Alfredo, Coutton, Charles, Dabir, Tabib, Dentici, Maria L., Devriendt, Koenraad, Faivre, Laurence, van Haelst, Mieke M., Jizi, Khadije, Kempers, Marlies J., Kerkhof, Jennifer, Kharbanda, Mira, Lachlan, Katherine, Marle, Nathalie, McConkey, Haley, Mencarelli, Maria A., Mowat, David., Niceta, Marcello, Nicolas, Claire, Novelli, Antonio, Orlando, Valeria, Pichon, Olivier, Rankin, Julia, Relator, Raissa., Ropers, Fabienne G., Rosenfeld, Jill A., Sachdev, Rani, Sandaradura, Sarah A., Shukarova-Angelovska, Elena, Steenbeek, Duco, Tartaglia, Marco, Tedder, Matthew A., Trajkova, Slavica, Winer, Norbert, Woods, Jeremy, de Vries, Bert B.A., Sadikovic, Bekim, Alders, Marielle, Santen, Gijs W.E.
Publikováno v:
In Genetics in Medicine January 2025 27(1)
In this paper we present 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 of AIDA is to propose on-the-spot the
Externí odkaz:
http://arxiv.org/abs/2112.13366