Results 41 to 50 of about 139,336 (244)
Deep Active Inference and Scene Construction
Frontiers in Artificial Intelligence, 2020 Adaptive agents must act in intrinsically uncertain environments with complex latent structure. Here, we elaborate a model of visual foraging—in a hierarchical context—wherein agents infer a higher-order visual pattern (a “scene”) by sequentially ...
R. Conor Heins +11 more
doaj +1 more source
Active Inference and Learning in the Cerebellum [PDF]
Neural Computation, 2016 This letter offers a computational account of Pavlovian conditioning in the cerebellum based on active inference and predictive coding. Using eyeblink conditioning as a canonical paradigm, we formulate a minimal generative model that can account for spontaneous blinking, startle responses, and (delay or trace) conditioning.
Karl J. Friston, Ivan Herreros-Alonso
openaire +3 more sources
Visual Search as Active Inference [PDF]
, 2020 Visual search is an essential cognitive ability, offering a prototypical control problem to be addressed with Active Inference. Under a Naive Bayes assumption, the maximization of the information gain objective is consistent with the separation of the visual sensory flow in two independent pathways, namely the “What” and the “Where” pathways.
Daucé, Emmanuel, Perrinet, Laurent U
openaire +1 more source
Deconstructing Deep Active Inference
, 2023 Active inference is a theory of perception, learning and decision making, which can be applied to neuroscience, robotics, and machine learning. Recently, reasearch has been taking place to scale up this framework using Monte-Carlo tree search and deep learning.
Théophile Champion +3 more
openaire +2 more sources
Active inference and the two-step task
Scientific Reports, 2022 Sequential decision problems distill important challenges frequently faced by humans. Through repeated interactions with an uncertain world, unknown statistics need to be learned while balancing exploration and exploitation.
Sam Gijsen +2 more
doaj +1 more source
Active inference and agency [PDF]
Cognitive Neuroscience, 2014 I greatly enjoyed Seth's compelling synthesis of sensorimotor contingencies and active inference. I would also like to thank Jim Hopkins for sending me the quote (below)-which speaks directly to the embodied nature of perceptual inference that underlies the perspectives reconciled in Seth (this issue).
openaire +2 more sources
Successor Representation Active Inference
CoRR, 2022 Recent work has uncovered close links between between classical reinforcement learning algorithms, Bayesian filtering, and Active Inference which lets us understand value functions in terms of Bayesian posteriors. An alternative, but less explored, model-free RL algorithm is the successor representation, which expresses the value function in terms of a
Beren Millidge, Christopher L. Buckley
openaire +2 more sources
The Free Energy Principle for Perception and Action: A Deep Learning Perspective
Entropy, 2022 The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states of the world, i.e., they minimize their free energy. Under this principle,
Pietro Mazzaglia +3 more
doaj +1 more source
Frontiers in SociologyGeneral intelligence enables flexible problem solving across diverse contexts by minimizing uncertainty. Symbolic systems such as language extend this capacity, allowing humans to build social groups and construct world models beyond typical biological ...
Shagor Rahman, Andrew Pashea
doaj +1 more source
Reinforcement learning or active inference?
PLoS ONE, 2009 This paper questions the need for reinforcement learning or control theory when optimising behaviour. We show that it is fairly simple to teach an agent complicated and adaptive behaviours using a free-energy formulation of perception.
Karl J Friston +2 more
doaj +1 more source