Results 61 to 70 of about 5,838,744 (309)
, 2023 The world consists of objects: distinct entities possessing independent properties and dynamics. For agents to interact with the world intelligently, they must translate sensory inputs into the bound-together features that describe each object. These object-based representations form a natural basis for planning behavior.
van Bergen, Ruben S., Lanillos, Pablo
openaire +3 more sources
Active Inference, Curiosity and Insight [PDF]
Neural Computation, 2017 This article offers a formal account of curiosity and insight in terms of active (Bayesian) inference. It deals with the dual problem of inferring states of the world and learning its statistical structure. In contrast to current trends in machine learning (e.g., deep learning), we focus on how people attain insight and understanding using just a ...
Friston Karl J +5 more
openaire +4 more sources
The cybernetic Bayesian brain: from interoceptive inference to sensorimotor contingencies [PDF]
, 2015 Is there a single principle by which neural operations can account for perception, cognition, action, and even consciousness? A strong candidate is now taking shape in the form of “predictive processing”.
Seth, Anil K
core +2 more sources
Active Inference for Integrated State-Estimation, Control, and Learning
, 2021 This work presents an approach for control, state-estimation and learning model (hyper)parameters for robotic manipulators. It is based on the active inference framework, prominent in computational neuroscience as a theory of the brain, where behaviour ...
Baioumy, Mohamed +3 more
core +1 more source
Time-consciousness in computational phenomenology: a temporal analysis of active inference
Neuroscience of Consciousness, 2023 Time plays a significant role in science and everyday life. Despite being experienced as a continuous flow, computational models of consciousness are typically restricted to a sequential temporal structure.
Juan Diego Bogotá, Z. Djebbara
semanticscholar +1 more source
A Variational Synthesis of Evolutionary and Developmental Dynamics
Entropy, 2023 This paper introduces a variational formulation of natural selection, paying special attention to the nature of ‘things’ and the way that different ‘kinds’ of ‘things’ are individuated from—and influence—each other.
Karl Friston +6 more
doaj +1 more source
Approximate inference in hidden Markov models using iterative active state selection [PDF]
, 2006 The inferential task of computing the marginal posterior probability mass functions of state variables and pairs of consecutive state variables of a hidden Markov model is considered.
Andrieu, C, Piechocki, RJ, Vithanage, CM
core +2 more sources
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
Canonical neural networks perform active inference
Communications Biology, 2022 Takuya Isomura, Hideaki Shimazaki and Karl Friston perform mathematical analysis to show that neural networks implicitly perform active inference and learning to minimise the risk associated with future outcomes.
Takuya Isomura +2 more
doaj +1 more source
Active Inference for Stochastic Control [PDF]
, 2021 12 pages, 5 figures, Accepted presentation at IWAI-2021 (ECML-PKDD)
Paul, Aswin +3 more
openaire +2 more sources