Results 1 to 10 of about 139,336 (244)

Intermittent Active Inference [PDF]

Entropy
Active inference provides a unified framework for perception and action as processes of minimizing prediction error given a generative model of the environment.
Markus Klar, Sebastian Stein, Fraser Paterson, John H. Williamson, Henrik Gollee, Roderick Murray-Smith   +5 more
doaj   +4 more sources

Embodied decisions as active inference. [PDF]

PLoS Computational Biology
Decision-making is often conceptualized as a serial process, during which sensory evidence is accumulated for the choice alternatives until a certain threshold is reached, at which point a decision is made and an action is executed.
Matteo Priorelli, Ivilin Peev Stoianov, Giovanni Pezzulo   +2 more
doaj   +5 more sources

Decision, Inference, and Information: Formal Equivalences Under Active Inference [PDF]

Entropy
A central challenge in artificial intelligence and cognitive science is identifying a unifying principle that governs inference, learning, and action. Active inference proposes such a principle: the minimization of variational free energy.
Patrick Sweeney, Jaime Ruiz-Serra, Michael S. Harré   +2 more
doaj   +2 more sources

The role of active inference in conscious awareness. [PDF]

PLoS ONE
Active inference, a first-principles framework for modelling the behaviour of sentient agents, is beginning to be applied in consciousness research. One hypothesis arising from the framework is that active inference is necessary for changes in conscious ...
Jonathan Edward Robinson, Andrew W Corcoran, Christopher J Whyte, András Sárközy, Anil K Seth, Gyula Kovács, Karl J Friston, Cyriel M A Pennartz, Giulio Tononi, Jakob Hohwy, TWCF: INTREPID Consortium   +10 more
doaj   +2 more sources

Active inference, morphogenesis, and computational psychiatry

Frontiers in Computational Neuroscience, 2022
Active inference is a leading theory in neuroscience that provides a simple and neuro-biologically plausible account of how action and perception are coupled in producing (Bayes) optimal behavior; and has been recently used to explain a variety of ...
Léo Pio-Lopez, Franz Kuchling, Angela Tung, Giovanni Pezzulo, Michael Levin, Michael Levin   +5 more
doaj   +3 more sources

Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop

Frontiers in Neurorobotics, 2018
Active inference is an ambitious theory that treats perception, inference, and action selection of autonomous agents under the heading of a single principle.
Martin Biehl, Christian Guckelsberger, Christoph Salge, Christoph Salge, Simón C. Smith, Simón C. Smith, Daniel Polani   +6 more
doaj   +3 more sources

Learning Generative State Space Models for Active Inference

Frontiers in Computational Neuroscience, 2020
In this paper we investigate the active inference framework as a means to enable autonomous behavior in artificial agents. Active inference is a theoretical framework underpinning the way organisms act and observe in the real world.
Ozan Çatal, Samuel Wauthier, Cedric De Boom, Tim Verbelen, Bart Dhoedt   +4 more
doaj   +3 more sources

An active inference account of stuttering behavior [PDF]

Frontiers in Human Neuroscience
This paper presents an interpretation of stuttering behavior, based on the principles of the active inference framework. Stuttering is a neurodevelopmental disorder characterized by speech disfluencies such as repetitions, prolongations, and blocks.
Evan Usler
doaj   +2 more sources

Representation Wars: Enacting an Armistice Through Active Inference

Frontiers in Psychology, 2021
Over the last 30 years, representationalist and dynamicist positions in the philosophy of cognitive science have argued over whether neurocognitive processes should be viewed as representational or not.
Axel Constant, Andy Clark, Andy Clark, Andy Clark, Karl J. Friston   +4 more
doaj   +3 more sources

The neural correlates of novelty and variability in human decision-making under an active inference framework [PDF]

eLife
Active inference integrates perception, decision-making, and learning into a united theoretical framework, providing an efficient way to trade off exploration and exploitation by minimizing (expected) free energy.
Shuo Zhang, Yan Tian, Quanying Liu, Haiyan Wu   +3 more
doaj   +2 more sources