Results 31 to 40 of about 4,744,312 (322)
Biological Cybernetics, 2018 This work combines the free energy principle from cognitive neuroscience and the ensuing active inference dynamics with recent advances in variational inference in deep generative models, and evolution strategies to introduce the "deep active inference" agent.
Kai Ueltzhöffer
openalex +6 more sources
Chance-Constrained Active Inference [PDF]
Neural Computation, 2021 Abstract Active inference (ActInf) is an emerging theory that explains perception and action in biological agents in terms of minimizing a free energy bound on Bayesian surprise. Goal-directed behavior is elicited by introducing prior beliefs on the underlying generative model.
van de Laar, Thijs +3 more
openaire +5 more sources
Scaling Active Inference [PDF]
2020 International Joint Conference on Neural Networks (IJCNN), 2020 In reinforcement learning (RL), agents often operate in partially observed and uncertain environments. Model-based RL suggests that this is best achieved by learning and exploiting a probabilistic model of the world. 'Active inference' is an emerging normative framework in cognitive and computational neuroscience that offers a unifying account of how ...
Tschantz, Alexander +3 more
openaire +2 more sources
Hunter–gatherer foraging networks promote information transmission
Royal Society Open Science, 2021 Central-place foraging (CPF), where foragers return to a central location (or home), is a key feature of hunter–gatherer social organization. CPF could have significantly changed hunter–gatherers’ spatial use and mobility, altered social networks and ...
Ketika Garg +3 more
doaj +1 more source
Active Inference for Stochastic Control [PDF]
, 2021 12 pages, 5 figures, Accepted presentation at IWAI-2021 (ECML-PKDD)
Aswin Paul +3 more
openalex +4 more sources
Active inference through whiskers [PDF]
Neural Networks, 2021 AbstractRodents use whisking to probe actively their environment and to locate objects in space, hence providing a paradigmatic biological example of active sensing. Numerous studies show that the control of whisking has anticipatory aspects. For example, rodents target their whisker protraction to the distance at which they expect objects, rather than
Mannella, Francesco +3 more
openaire +2 more sources
Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making [PDF]
International Workshop on Affective Interactions, 2023 This paper investigates the prospect of developing human-interpretable, explainable artificial intelligence (AI) systems based on active inference and the free energy principle. We first provide a brief overview of active inference, and in particular, of
Mahault Albarracin +6 more
semanticscholar +1 more source
Control Flow in Active Inference Systems—Part I: Classical and Quantum Formulations of Active Inference [PDF]
IEEE Transactions on Molecular Biological and Multi-Scale Communications, 2023 Living systems face both environmental complexity and limited access to free-energy resources. Survival under these conditions requires a control system that can activate, or deploy, available perception and action resources in a context specific way. In
C. Fields +6 more
semanticscholar +1 more source
Modeling Motor Control in Continuous Time Active Inference: A Survey [PDF]
IEEE Transactions on Cognitive and Developmental Systems, 2023 The way the brain selects and controls actions is still widely debated. Mainstream approaches based on optimal control focus on stimulus-response mappings that optimize cost functions.
Matteo Priorelli +7 more
semanticscholar +1 more source
, 2021 Active inference is a unifying theory for perception and action resting upon the idea that the brain maintains an internal model of the world by minimizing free energy. From a behavioral perspective, active inference agents can be seen as self-evidencing beings that act to fulfill their optimistic predictions, namely preferred outcomes or goals.
Mazzaglia, Pietro +2 more
openaire +3 more sources