Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311562297> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4311562297 abstract "Every organism in an environment, whether biological, robotic or virtual, must be able to predict certain aspects of its environment in order to survive or perform whatever task is intended. It needs a model that is capable of estimating the consequences of possible actions, so that planning, control, and decision-making become feasible. For scientific purposes, such models are usually created in a problem specific manner using differential equations and other techniques from control- and system-theory. In contrast to that, we aim for an unsupervised approach that builds up the desired model in a self-organized fashion. Inspired by Slow Feature Analysis (SFA), our approach is to extract sub-signals from the input, that behave as predictable as possible. These predictable features are highly relevant for modeling, because predictability is a desired property of the needed consequence-estimating model by definition. In our approach, we measure predictability with respect to a certain prediction model. We focus here on the solution of the arising optimization problem and present a tractable algorithm based on algebraic methods which we call Predictable Feature Analysis (PFA). We prove that the algorithm finds the globally optimal signal, if this signal can be predicted with low error. To deal with cases where the optimal signal has a significant prediction error, we provide a robust, heuristically motivated variant of the algorithm and verify it empirically. Additionally, we give formal criteria a prediction-model must meet to be suitable for measuring predictability in the PFA setting and also provide a suitable default-model along with a formal proof that it meets these criteria." @default.
- W4311562297 created "2022-12-27" @default.
- W4311562297 creator A5039663126 @default.
- W4311562297 creator A5079967303 @default.
- W4311562297 date "2013-11-11" @default.
- W4311562297 modified "2023-09-26" @default.
- W4311562297 title "Predictable Feature Analysis" @default.
- W4311562297 doi "https://doi.org/10.48550/arxiv.1311.2503" @default.
- W4311562297 hasPublicationYear "2013" @default.
- W4311562297 type Work @default.
- W4311562297 citedByCount "0" @default.
- W4311562297 crossrefType "posted-content" @default.
- W4311562297 hasAuthorship W4311562297A5039663126 @default.
- W4311562297 hasAuthorship W4311562297A5079967303 @default.
- W4311562297 hasBestOaLocation W43115622971 @default.
- W4311562297 hasConcept C105795698 @default.
- W4311562297 hasConcept C111472728 @default.
- W4311562297 hasConcept C11413529 @default.
- W4311562297 hasConcept C119857082 @default.
- W4311562297 hasConcept C120665830 @default.
- W4311562297 hasConcept C121332964 @default.
- W4311562297 hasConcept C124101348 @default.
- W4311562297 hasConcept C138885662 @default.
- W4311562297 hasConcept C154945302 @default.
- W4311562297 hasConcept C162324750 @default.
- W4311562297 hasConcept C187736073 @default.
- W4311562297 hasConcept C189950617 @default.
- W4311562297 hasConcept C192209626 @default.
- W4311562297 hasConcept C197640229 @default.
- W4311562297 hasConcept C199360897 @default.
- W4311562297 hasConcept C2776401178 @default.
- W4311562297 hasConcept C2776502983 @default.
- W4311562297 hasConcept C2779843651 @default.
- W4311562297 hasConcept C2780009758 @default.
- W4311562297 hasConcept C2780451532 @default.
- W4311562297 hasConcept C33923547 @default.
- W4311562297 hasConcept C41008148 @default.
- W4311562297 hasConcept C41895202 @default.
- W4311562297 hasConceptScore W4311562297C105795698 @default.
- W4311562297 hasConceptScore W4311562297C111472728 @default.
- W4311562297 hasConceptScore W4311562297C11413529 @default.
- W4311562297 hasConceptScore W4311562297C119857082 @default.
- W4311562297 hasConceptScore W4311562297C120665830 @default.
- W4311562297 hasConceptScore W4311562297C121332964 @default.
- W4311562297 hasConceptScore W4311562297C124101348 @default.
- W4311562297 hasConceptScore W4311562297C138885662 @default.
- W4311562297 hasConceptScore W4311562297C154945302 @default.
- W4311562297 hasConceptScore W4311562297C162324750 @default.
- W4311562297 hasConceptScore W4311562297C187736073 @default.
- W4311562297 hasConceptScore W4311562297C189950617 @default.
- W4311562297 hasConceptScore W4311562297C192209626 @default.
- W4311562297 hasConceptScore W4311562297C197640229 @default.
- W4311562297 hasConceptScore W4311562297C199360897 @default.
- W4311562297 hasConceptScore W4311562297C2776401178 @default.
- W4311562297 hasConceptScore W4311562297C2776502983 @default.
- W4311562297 hasConceptScore W4311562297C2779843651 @default.
- W4311562297 hasConceptScore W4311562297C2780009758 @default.
- W4311562297 hasConceptScore W4311562297C2780451532 @default.
- W4311562297 hasConceptScore W4311562297C33923547 @default.
- W4311562297 hasConceptScore W4311562297C41008148 @default.
- W4311562297 hasConceptScore W4311562297C41895202 @default.
- W4311562297 hasLocation W43115622971 @default.
- W4311562297 hasLocation W43115622972 @default.
- W4311562297 hasOpenAccess W4311562297 @default.
- W4311562297 hasPrimaryLocation W43115622971 @default.
- W4311562297 hasRelatedWork W1527837723 @default.
- W4311562297 hasRelatedWork W1974962040 @default.
- W4311562297 hasRelatedWork W1977478121 @default.
- W4311562297 hasRelatedWork W2018140895 @default.
- W4311562297 hasRelatedWork W2065137470 @default.
- W4311562297 hasRelatedWork W2118112569 @default.
- W4311562297 hasRelatedWork W2350743277 @default.
- W4311562297 hasRelatedWork W2790014886 @default.
- W4311562297 hasRelatedWork W2961085424 @default.
- W4311562297 hasRelatedWork W4306674287 @default.
- W4311562297 isParatext "false" @default.
- W4311562297 isRetracted "false" @default.
- W4311562297 workType "article" @default.