Matches in SemOpenAlex for { <https://semopenalex.org/work/W2320570172> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2320570172 abstract "This thesis investigates the potential of generative neural networks to model cognitive processes. In contrast to many popular connectionist models, the computational framework adopted in this research work emphasizes the generative nature of cognition, suggesting that one of the primary goals of cognitive systems is to learn an internal model of the surrounding environment that can be used to infer causes and make predictions about the upcoming sensory information. In particular, we consider a powerful class of recurrent neural networks that learn probabilistic generative models from experience in a completely unsupervised way, by extracting high-order statistical structure from a set of observed variables. Notably, this type of networks can be conveniently formalized within the more general framework of probabilistic graphical models, which provides a unified language to describe both neural networks and structured Bayesian models. Moreover, recent advances allow to extend basic network architectures to build more powerful systems, which exploit multiple processing stages to perform learning and inference over hierarchical models, or which exploit delayed recurrent connections to process sequential information. We argue that these advanced network architectures constitute a promising alternative to the more traditional, feed-forward, supervised neural networks, because they more neatly capture the functional and structural organization of cortical circuits, providing a principled way to combine top-down, high-level contextual information with bottom-up, sensory evidence. We provide empirical support justifying the use of these models by studying how efficient implementations of hierarchical and temporal generative networks can extract information from large datasets containing thousands of patterns. In particular, we perform computational simulations of recognition of handwritten and printed characters belonging to different writing scripts, which are successively combined spatially or temporally in order to build more complex orthographic units such as those constituting English words." @default.
- W2320570172 created "2016-06-24" @default.
- W2320570172 creator A5027874987 @default.
- W2320570172 date "2015-01-01" @default.
- W2320570172 modified "2023-09-23" @default.
- W2320570172 title "Modeling cognition with generative neural networks: The case of orthographic processing" @default.
- W2320570172 hasPublicationYear "2015" @default.
- W2320570172 type Work @default.
- W2320570172 sameAs 2320570172 @default.
- W2320570172 citedByCount "0" @default.
- W2320570172 crossrefType "journal-article" @default.
- W2320570172 hasAuthorship W2320570172A5027874987 @default.
- W2320570172 hasConcept C119857082 @default.
- W2320570172 hasConcept C154945302 @default.
- W2320570172 hasConcept C155846161 @default.
- W2320570172 hasConcept C165696696 @default.
- W2320570172 hasConcept C167966045 @default.
- W2320570172 hasConcept C177264268 @default.
- W2320570172 hasConcept C199360897 @default.
- W2320570172 hasConcept C2776214188 @default.
- W2320570172 hasConcept C38652104 @default.
- W2320570172 hasConcept C39890363 @default.
- W2320570172 hasConcept C41008148 @default.
- W2320570172 hasConcept C49937458 @default.
- W2320570172 hasConcept C50644808 @default.
- W2320570172 hasConcept C8521452 @default.
- W2320570172 hasConceptScore W2320570172C119857082 @default.
- W2320570172 hasConceptScore W2320570172C154945302 @default.
- W2320570172 hasConceptScore W2320570172C155846161 @default.
- W2320570172 hasConceptScore W2320570172C165696696 @default.
- W2320570172 hasConceptScore W2320570172C167966045 @default.
- W2320570172 hasConceptScore W2320570172C177264268 @default.
- W2320570172 hasConceptScore W2320570172C199360897 @default.
- W2320570172 hasConceptScore W2320570172C2776214188 @default.
- W2320570172 hasConceptScore W2320570172C38652104 @default.
- W2320570172 hasConceptScore W2320570172C39890363 @default.
- W2320570172 hasConceptScore W2320570172C41008148 @default.
- W2320570172 hasConceptScore W2320570172C49937458 @default.
- W2320570172 hasConceptScore W2320570172C50644808 @default.
- W2320570172 hasConceptScore W2320570172C8521452 @default.
- W2320570172 hasLocation W23205701721 @default.
- W2320570172 hasOpenAccess W2320570172 @default.
- W2320570172 hasPrimaryLocation W23205701721 @default.
- W2320570172 hasRelatedWork W127439518 @default.
- W2320570172 hasRelatedWork W190483326 @default.
- W2320570172 hasRelatedWork W1917177419 @default.
- W2320570172 hasRelatedWork W2052055672 @default.
- W2320570172 hasRelatedWork W2124151298 @default.
- W2320570172 hasRelatedWork W2130289607 @default.
- W2320570172 hasRelatedWork W2140661072 @default.
- W2320570172 hasRelatedWork W2464471615 @default.
- W2320570172 hasRelatedWork W2600595719 @default.
- W2320570172 hasRelatedWork W2948981535 @default.
- W2320570172 hasRelatedWork W2962883855 @default.
- W2320570172 hasRelatedWork W2963633072 @default.
- W2320570172 hasRelatedWork W2963841039 @default.
- W2320570172 hasRelatedWork W2990677997 @default.
- W2320570172 hasRelatedWork W3096274078 @default.
- W2320570172 hasRelatedWork W3122623456 @default.
- W2320570172 hasRelatedWork W3153238932 @default.
- W2320570172 hasRelatedWork W3203750989 @default.
- W2320570172 hasRelatedWork W60533568 @default.
- W2320570172 hasRelatedWork W764470327 @default.
- W2320570172 isParatext "false" @default.
- W2320570172 isRetracted "false" @default.
- W2320570172 magId "2320570172" @default.
- W2320570172 workType "article" @default.