Matches in SemOpenAlex for { <https://semopenalex.org/work/W9948473> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W9948473 abstract "It is well known that the human brain is highly modular, having a structural and functional organization that allows the different regions of the brain to be reused for different cognitive processes. So far, this has not been fully addressed by artificial systems, and a better understanding of when and how modules emerge is required, with a broad framework indicating how modules could be reused within neural networks. This thesis provides a deep investigation of module formation, module communication (interaction) and module reuse during evolution for a variety of classification and prediction tasks. The evolutionary algorithm EPNet is used to deliver the evolution of artificial neural networks. In the first stage of this study, the EPNet algorithm is carefully studied to understand its basis and to ensure confidence in its behaviour. Thereafter, its input feature selection (required for module evolution) is optimized, showing the robustness of the improved algorithm compared with the fixed input case and previous publications. Then module emergence, communication and reuse are investigated with the modular EPNet (M-EPNet) algorithm, which uses the information provided by a modularity measure to implement new mutation operators that favour the evolution of modules, allowing a new perspective for analyzing modularity, module formation and module reuse during evolution.The results obtained extend those of previous work, indicating that pure-modular architectures may emerge at low connectivity values, where similar tasks may share (reuse) common neural elements creating compact representations, and that the more different two tasks are, the bigger the modularity obtained during evolution. Other results indicate that some neural structures may be reused when similar tasks are evolved, leading to module interaction during evolution." @default.
- W9948473 created "2016-06-24" @default.
- W9948473 creator A5064144252 @default.
- W9948473 creator A5073844588 @default.
- W9948473 date "2012-07-01" @default.
- W9948473 modified "2023-09-23" @default.
- W9948473 title "Evolution of modular neural networks" @default.
- W9948473 hasPublicationYear "2012" @default.
- W9948473 type Work @default.
- W9948473 sameAs 9948473 @default.
- W9948473 citedByCount "1" @default.
- W9948473 countsByYear W99484732018 @default.
- W9948473 crossrefType "dissertation" @default.
- W9948473 hasAuthorship W9948473A5064144252 @default.
- W9948473 hasAuthorship W9948473A5073844588 @default.
- W9948473 hasConcept C101468663 @default.
- W9948473 hasConcept C104317684 @default.
- W9948473 hasConcept C120314980 @default.
- W9948473 hasConcept C127413603 @default.
- W9948473 hasConcept C154945302 @default.
- W9948473 hasConcept C159149176 @default.
- W9948473 hasConcept C185592680 @default.
- W9948473 hasConcept C199360897 @default.
- W9948473 hasConcept C206588197 @default.
- W9948473 hasConcept C2779478453 @default.
- W9948473 hasConcept C41008148 @default.
- W9948473 hasConcept C50644808 @default.
- W9948473 hasConcept C54355233 @default.
- W9948473 hasConcept C548081761 @default.
- W9948473 hasConcept C55493867 @default.
- W9948473 hasConcept C63479239 @default.
- W9948473 hasConcept C80444323 @default.
- W9948473 hasConcept C86803240 @default.
- W9948473 hasConceptScore W9948473C101468663 @default.
- W9948473 hasConceptScore W9948473C104317684 @default.
- W9948473 hasConceptScore W9948473C120314980 @default.
- W9948473 hasConceptScore W9948473C127413603 @default.
- W9948473 hasConceptScore W9948473C154945302 @default.
- W9948473 hasConceptScore W9948473C159149176 @default.
- W9948473 hasConceptScore W9948473C185592680 @default.
- W9948473 hasConceptScore W9948473C199360897 @default.
- W9948473 hasConceptScore W9948473C206588197 @default.
- W9948473 hasConceptScore W9948473C2779478453 @default.
- W9948473 hasConceptScore W9948473C41008148 @default.
- W9948473 hasConceptScore W9948473C50644808 @default.
- W9948473 hasConceptScore W9948473C54355233 @default.
- W9948473 hasConceptScore W9948473C548081761 @default.
- W9948473 hasConceptScore W9948473C55493867 @default.
- W9948473 hasConceptScore W9948473C63479239 @default.
- W9948473 hasConceptScore W9948473C80444323 @default.
- W9948473 hasConceptScore W9948473C86803240 @default.
- W9948473 hasLocation W99484731 @default.
- W9948473 hasOpenAccess W9948473 @default.
- W9948473 hasPrimaryLocation W99484731 @default.
- W9948473 hasRelatedWork W107839348 @default.
- W9948473 hasRelatedWork W1712389766 @default.
- W9948473 hasRelatedWork W1974955624 @default.
- W9948473 hasRelatedWork W2007073506 @default.
- W9948473 hasRelatedWork W2017303659 @default.
- W9948473 hasRelatedWork W2072902767 @default.
- W9948473 hasRelatedWork W2074980356 @default.
- W9948473 hasRelatedWork W2098613749 @default.
- W9948473 hasRelatedWork W2113561847 @default.
- W9948473 hasRelatedWork W2145965216 @default.
- W9948473 hasRelatedWork W2157606016 @default.
- W9948473 hasRelatedWork W2167021024 @default.
- W9948473 hasRelatedWork W2170478264 @default.
- W9948473 hasRelatedWork W2186649378 @default.
- W9948473 hasRelatedWork W2346104046 @default.
- W9948473 hasRelatedWork W2589843926 @default.
- W9948473 hasRelatedWork W2750556708 @default.
- W9948473 hasRelatedWork W2888099897 @default.
- W9948473 hasRelatedWork W349863322 @default.
- W9948473 hasRelatedWork W2339540021 @default.
- W9948473 isParatext "false" @default.
- W9948473 isRetracted "false" @default.
- W9948473 magId "9948473" @default.
- W9948473 workType "dissertation" @default.