Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899509766> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2899509766 endingPage "120" @default.
- W2899509766 startingPage "109" @default.
- W2899509766 abstract "Within the field of cognitive neuroscience, predictive processing is an increasingly popular unifying account of cognitive capacities including action and perception which posits that these rely on probabilistic generative models to predict sensory input or the consequences of one’s behaviour. In the corresponding literature one frequently encounters naive claims about the computational resources required to successfully employ such models, while actual complexity analyses are often lacking. In this paper we study the problem of selecting a course of action which yields the greatest reduction in prediction error between the intended outcome and the current state, known in this area as textit{active inference}. Modelling the problem in terms of Bayesian networks and the relative entropy (Kullback-Leibler divergence) between a target and an induced distribution, we derive parameterized (in)tractability results extending the NPPP-hardness classification found in Kwisthout 2014. These show that contrary to common belief, the size of the prediction error does not determine whether active inference is tractable, not even when the number of actions and outcomes to be considered is restricted. Moreover, this conclusion appears to extend even to an approximate version of the problem. We believe these results can be of interest to both cognitive scientists seeking to evaluate the plausibility of their explanatory theories, and to researchers working on probabilistic models, as they relate to existing work on the hardness of observation selection in decision making." @default.
- W2899509766 created "2018-11-09" @default.
- W2899509766 creator A5044987235 @default.
- W2899509766 date "2018-08-28" @default.
- W2899509766 modified "2023-09-28" @default.
- W2899509766 title "Parameterized hardness of active inference" @default.
- W2899509766 hasPublicationYear "2018" @default.
- W2899509766 type Work @default.
- W2899509766 sameAs 2899509766 @default.
- W2899509766 citedByCount "0" @default.
- W2899509766 crossrefType "proceedings-article" @default.
- W2899509766 hasAuthorship W2899509766A5044987235 @default.
- W2899509766 hasConcept C106301342 @default.
- W2899509766 hasConcept C107673813 @default.
- W2899509766 hasConcept C11413529 @default.
- W2899509766 hasConcept C119857082 @default.
- W2899509766 hasConcept C121332964 @default.
- W2899509766 hasConcept C154945302 @default.
- W2899509766 hasConcept C15744967 @default.
- W2899509766 hasConcept C160234255 @default.
- W2899509766 hasConcept C165464430 @default.
- W2899509766 hasConcept C166109690 @default.
- W2899509766 hasConcept C169760540 @default.
- W2899509766 hasConcept C169900460 @default.
- W2899509766 hasConcept C171752962 @default.
- W2899509766 hasConcept C26760741 @default.
- W2899509766 hasConcept C2776214188 @default.
- W2899509766 hasConcept C41008148 @default.
- W2899509766 hasConcept C49937458 @default.
- W2899509766 hasConcept C62520636 @default.
- W2899509766 hasConcept C9679016 @default.
- W2899509766 hasConceptScore W2899509766C106301342 @default.
- W2899509766 hasConceptScore W2899509766C107673813 @default.
- W2899509766 hasConceptScore W2899509766C11413529 @default.
- W2899509766 hasConceptScore W2899509766C119857082 @default.
- W2899509766 hasConceptScore W2899509766C121332964 @default.
- W2899509766 hasConceptScore W2899509766C154945302 @default.
- W2899509766 hasConceptScore W2899509766C15744967 @default.
- W2899509766 hasConceptScore W2899509766C160234255 @default.
- W2899509766 hasConceptScore W2899509766C165464430 @default.
- W2899509766 hasConceptScore W2899509766C166109690 @default.
- W2899509766 hasConceptScore W2899509766C169760540 @default.
- W2899509766 hasConceptScore W2899509766C169900460 @default.
- W2899509766 hasConceptScore W2899509766C171752962 @default.
- W2899509766 hasConceptScore W2899509766C26760741 @default.
- W2899509766 hasConceptScore W2899509766C2776214188 @default.
- W2899509766 hasConceptScore W2899509766C41008148 @default.
- W2899509766 hasConceptScore W2899509766C49937458 @default.
- W2899509766 hasConceptScore W2899509766C62520636 @default.
- W2899509766 hasConceptScore W2899509766C9679016 @default.
- W2899509766 hasLocation W28995097661 @default.
- W2899509766 hasOpenAccess W2899509766 @default.
- W2899509766 hasPrimaryLocation W28995097661 @default.
- W2899509766 hasRelatedWork W1596125777 @default.
- W2899509766 hasRelatedWork W1993121415 @default.
- W2899509766 hasRelatedWork W2042359577 @default.
- W2899509766 hasRelatedWork W2106478918 @default.
- W2899509766 hasRelatedWork W2121832778 @default.
- W2899509766 hasRelatedWork W2130623327 @default.
- W2899509766 hasRelatedWork W2134922236 @default.
- W2899509766 hasRelatedWork W2157201325 @default.
- W2899509766 hasRelatedWork W2173207635 @default.
- W2899509766 hasRelatedWork W2284232573 @default.
- W2899509766 hasRelatedWork W240841704 @default.
- W2899509766 hasRelatedWork W2614978932 @default.
- W2899509766 hasRelatedWork W2619015219 @default.
- W2899509766 hasRelatedWork W2804810839 @default.
- W2899509766 hasRelatedWork W2952500605 @default.
- W2899509766 hasRelatedWork W2976973594 @default.
- W2899509766 hasRelatedWork W3008126392 @default.
- W2899509766 hasRelatedWork W3013065462 @default.
- W2899509766 hasRelatedWork W3099663651 @default.
- W2899509766 hasRelatedWork W3100307197 @default.
- W2899509766 hasVolume "72" @default.
- W2899509766 isParatext "false" @default.
- W2899509766 isRetracted "false" @default.
- W2899509766 magId "2899509766" @default.
- W2899509766 workType "article" @default.