Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210837145> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4210837145 endingPage "197" @default.
- W4210837145 startingPage "197" @default.
- W4210837145 abstract "A neural network learning paradigm based on information theory is proposed as a way to perform, in an unsupervised fashion, redundancy reduction among the elements of the output layer without loss of information from the sensory input. The model developed performs nonlinear decorrelation up to higher orders of the cumulant tensors and results in probabilistically independent components of the output layer. This means that we don't need to assume Gaussian distribution at either the input or the output. The theory presented is related to the unsupervised learning theory of Barlow, which proposes redundancy reduction as the goal of cognition. When nonlinear units are used (sigmoid or higher-order pi-neurons), nonlinear principal component analysis is obtained. In this case, nonlinear manifolds can be reduced to minimum dimension manifolds. If such units are used the network performs a generalized principal component analysis in the sense that non-Gaussian distributions can be linearly decorrelated and higher orders of the correlation tensors are also taken into account. The basic structure of the architecture involves a general transformation that is volume conserving and therefore the entropy, yielding a map without loss of information. Minimization of the mutual information among the output neurons eliminates the redundancy between the outputs and results in statistical decorrelation of the extracted features. This is known as factorial learning. To sum up, this paper presents a model of factorial learning for general nonlinear transformations of an arbitrary non-Gaussian (or Gaussian) environment with statistically nonlinearly correlated input. Simulations demonstrate the effectiveness of this method." @default.
- W4210837145 created "2022-02-09" @default.
- W4210837145 date "1998-05-01" @default.
- W4210837145 modified "2023-09-26" @default.
- W4210837145 title "98/02179 Probabilistic ranking of large scale transmission projects" @default.
- W4210837145 doi "https://doi.org/10.1016/s0140-6701(98)80381-0" @default.
- W4210837145 hasPublicationYear "1998" @default.
- W4210837145 type Work @default.
- W4210837145 citedByCount "0" @default.
- W4210837145 crossrefType "journal-article" @default.
- W4210837145 hasConcept C105795698 @default.
- W4210837145 hasConcept C106301342 @default.
- W4210837145 hasConcept C111919701 @default.
- W4210837145 hasConcept C11413529 @default.
- W4210837145 hasConcept C121332964 @default.
- W4210837145 hasConcept C152124472 @default.
- W4210837145 hasConcept C152139883 @default.
- W4210837145 hasConcept C153180895 @default.
- W4210837145 hasConcept C154945302 @default.
- W4210837145 hasConcept C158622935 @default.
- W4210837145 hasConcept C163716315 @default.
- W4210837145 hasConcept C177860922 @default.
- W4210837145 hasConcept C27438332 @default.
- W4210837145 hasConcept C33923547 @default.
- W4210837145 hasConcept C41008148 @default.
- W4210837145 hasConcept C49937458 @default.
- W4210837145 hasConcept C50644808 @default.
- W4210837145 hasConcept C52622258 @default.
- W4210837145 hasConcept C62520636 @default.
- W4210837145 hasConcept C81388566 @default.
- W4210837145 hasConceptScore W4210837145C105795698 @default.
- W4210837145 hasConceptScore W4210837145C106301342 @default.
- W4210837145 hasConceptScore W4210837145C111919701 @default.
- W4210837145 hasConceptScore W4210837145C11413529 @default.
- W4210837145 hasConceptScore W4210837145C121332964 @default.
- W4210837145 hasConceptScore W4210837145C152124472 @default.
- W4210837145 hasConceptScore W4210837145C152139883 @default.
- W4210837145 hasConceptScore W4210837145C153180895 @default.
- W4210837145 hasConceptScore W4210837145C154945302 @default.
- W4210837145 hasConceptScore W4210837145C158622935 @default.
- W4210837145 hasConceptScore W4210837145C163716315 @default.
- W4210837145 hasConceptScore W4210837145C177860922 @default.
- W4210837145 hasConceptScore W4210837145C27438332 @default.
- W4210837145 hasConceptScore W4210837145C33923547 @default.
- W4210837145 hasConceptScore W4210837145C41008148 @default.
- W4210837145 hasConceptScore W4210837145C49937458 @default.
- W4210837145 hasConceptScore W4210837145C50644808 @default.
- W4210837145 hasConceptScore W4210837145C52622258 @default.
- W4210837145 hasConceptScore W4210837145C62520636 @default.
- W4210837145 hasConceptScore W4210837145C81388566 @default.
- W4210837145 hasIssue "3" @default.
- W4210837145 hasLocation W42108371451 @default.
- W4210837145 hasOpenAccess W4210837145 @default.
- W4210837145 hasPrimaryLocation W42108371451 @default.
- W4210837145 hasRelatedWork W1550191592 @default.
- W4210837145 hasRelatedWork W1976025425 @default.
- W4210837145 hasRelatedWork W2103378973 @default.
- W4210837145 hasRelatedWork W2112100270 @default.
- W4210837145 hasRelatedWork W2151857959 @default.
- W4210837145 hasRelatedWork W2561486997 @default.
- W4210837145 hasRelatedWork W2941406960 @default.
- W4210837145 hasRelatedWork W2993993911 @default.
- W4210837145 hasRelatedWork W3032136380 @default.
- W4210837145 hasRelatedWork W3095260183 @default.
- W4210837145 hasVolume "39" @default.
- W4210837145 isParatext "false" @default.
- W4210837145 isRetracted "false" @default.
- W4210837145 workType "article" @default.