Zobrazeno 1 - 10
of 232
pro vyhledávání: '"Aguilera, Miguel A."'
Higher-order interactions underlie complex phenomena in systems such as biological and artificial neural networks, but their study is challenging due to the lack of tractable standard models. By leveraging the maximum entropy principle in curved stat
Externí odkaz:
http://arxiv.org/abs/2408.02326
Autor:
Poc-López, Ángel, Aguilera, Miguel
Transformer-based models have demonstrated exceptional performance across diverse domains, becoming the state-of-the-art solution for addressing sequential machine learning problems. Even though we have a general understanding of the fundamental comp
Externí odkaz:
http://arxiv.org/abs/2406.07247
The growing popularity of Machine Learning (ML) has led to its deployment in various sensitive domains, which has resulted in significant research focused on ML security and privacy. However, in some applications, such as Augmented/Virtual Reality, i
Externí odkaz:
http://arxiv.org/abs/2304.00083
Bayesian theories of biological and brain function speculate that Markov blankets (a conditional independence separating a system from external states) play a key role for facilitating inference-like behaviour in living systems. Although it has been
Externí odkaz:
http://arxiv.org/abs/2207.12914
An open question in the study of emergent behaviour in multi-agent Bayesian systems is the relationship, if any, between individual and collective inference. In this paper we explore the correspondence between generative models that exist at two dist
Externí odkaz:
http://arxiv.org/abs/2207.06970
Publikováno v:
Nature Communications 14, 3685 (2023)
Most natural systems operate far from equilibrium, displaying time-asymmetric, irreversible dynamics characterized by a positive entropy production while exchanging energy and matter with the environment. Although stochastic thermodynamics underpins
Externí odkaz:
http://arxiv.org/abs/2205.09886
Autor:
Poc-López, Ángel, Aguilera, Miguel
Publikováno v:
International Conference on Neural Information Processing 2021
We extend previous mean-field approaches for non-equilibrium neural network models to estimate correlations in the system. This offers a powerful tool for approximating the system dynamics as well as a fast method to infer network parameters from obs
Externí odkaz:
http://arxiv.org/abs/2107.06850
Publikováno v:
Physics of Life Reviews. Volume 40, March 2022, Pages 24-50
The free energy principle (FEP) states that any dynamical system can be interpreted as performing Bayesian inference upon its surrounding environment. In this work, we examine in depth the assumptions required to derive the FEP in the simplest possib
Externí odkaz:
http://arxiv.org/abs/2105.11203
Publikováno v:
Nature Communications 12, 1197 (2021)
Kinetic Ising models are powerful tools for studying the non-equilibrium dynamics of complex systems. As their behavior is not tractable for large networks, many mean-field methods have been proposed for their analysis, each based on unique assumptio
Externí odkaz:
http://arxiv.org/abs/2002.04309
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.