Matches in SemOpenAlex for { <https://semopenalex.org/work/W2884328272> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2884328272 abstract "Majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability. The existing neuro-evolution of augmenting topology or NEAT paradigm offers a powerful alternative by allowing the network topology and the connection weights to be simultaneously optimized through an evolutionary process. However, most NEAT implementations allow the consideration of only a single objective. There also persists the question of how to tractably introduce topological diversification that mitigates overfitting to training scenarios. To address these gaps, this paper develops a multi-objective neuro-evolution algorithm. While adopting the basic elements of NEAT, important modifications are made to the selection, speciation, and mutation processes. With the backdrop of small-robot path-planning applications, an experience-gain criterion is derived to encapsulate the amount of diverse local environment encountered by the system. This criterion facilitates the evolution of genes that support exploration, thereby seeking to generalize from a smaller set of mission scenarios than possible with performance maximization alone. The effectiveness of the single-objective (optimizing performance) and the multi-objective (optimizing performance and experience-gain) neuro-evolution approaches are evaluated on two different small-robot cases, with ANNs obtained by the multi-objective optimization observed to provide superior performance in unseen scenarios." @default.
- W2884328272 created "2018-08-03" @default.
- W2884328272 creator A5044702596 @default.
- W2884328272 creator A5074202796 @default.
- W2884328272 creator A5090040051 @default.
- W2884328272 date "2018-08-26" @default.
- W2884328272 modified "2023-10-16" @default.
- W2884328272 title "Multi-Criteria Evolution of Neural Network Topologies: Balancing Experience and Performance in Autonomous Systems" @default.
- W2884328272 doi "https://doi.org/10.1115/detc2018-86104" @default.
- W2884328272 hasPublicationYear "2018" @default.
- W2884328272 type Work @default.
- W2884328272 sameAs 2884328272 @default.
- W2884328272 citedByCount "3" @default.
- W2884328272 countsByYear W28843282722019 @default.
- W2884328272 crossrefType "proceedings-article" @default.
- W2884328272 hasAuthorship W2884328272A5044702596 @default.
- W2884328272 hasAuthorship W2884328272A5074202796 @default.
- W2884328272 hasAuthorship W2884328272A5090040051 @default.
- W2884328272 hasBestOaLocation W28843282722 @default.
- W2884328272 hasConcept C111919701 @default.
- W2884328272 hasConcept C119599485 @default.
- W2884328272 hasConcept C120314980 @default.
- W2884328272 hasConcept C126255220 @default.
- W2884328272 hasConcept C127413603 @default.
- W2884328272 hasConcept C154945302 @default.
- W2884328272 hasConcept C159149176 @default.
- W2884328272 hasConcept C184720557 @default.
- W2884328272 hasConcept C199360897 @default.
- W2884328272 hasConcept C199845137 @default.
- W2884328272 hasConcept C207002847 @default.
- W2884328272 hasConcept C22019652 @default.
- W2884328272 hasConcept C26713055 @default.
- W2884328272 hasConcept C2776330181 @default.
- W2884328272 hasConcept C33923547 @default.
- W2884328272 hasConcept C41008148 @default.
- W2884328272 hasConcept C50644808 @default.
- W2884328272 hasConcept C63000827 @default.
- W2884328272 hasConceptScore W2884328272C111919701 @default.
- W2884328272 hasConceptScore W2884328272C119599485 @default.
- W2884328272 hasConceptScore W2884328272C120314980 @default.
- W2884328272 hasConceptScore W2884328272C126255220 @default.
- W2884328272 hasConceptScore W2884328272C127413603 @default.
- W2884328272 hasConceptScore W2884328272C154945302 @default.
- W2884328272 hasConceptScore W2884328272C159149176 @default.
- W2884328272 hasConceptScore W2884328272C184720557 @default.
- W2884328272 hasConceptScore W2884328272C199360897 @default.
- W2884328272 hasConceptScore W2884328272C199845137 @default.
- W2884328272 hasConceptScore W2884328272C207002847 @default.
- W2884328272 hasConceptScore W2884328272C22019652 @default.
- W2884328272 hasConceptScore W2884328272C26713055 @default.
- W2884328272 hasConceptScore W2884328272C2776330181 @default.
- W2884328272 hasConceptScore W2884328272C33923547 @default.
- W2884328272 hasConceptScore W2884328272C41008148 @default.
- W2884328272 hasConceptScore W2884328272C50644808 @default.
- W2884328272 hasConceptScore W2884328272C63000827 @default.
- W2884328272 hasLocation W28843282721 @default.
- W2884328272 hasLocation W28843282722 @default.
- W2884328272 hasOpenAccess W2884328272 @default.
- W2884328272 hasPrimaryLocation W28843282721 @default.
- W2884328272 hasRelatedWork W1504189285 @default.
- W2884328272 hasRelatedWork W1561327184 @default.
- W2884328272 hasRelatedWork W1571147990 @default.
- W2884328272 hasRelatedWork W2064713504 @default.
- W2884328272 hasRelatedWork W2073451469 @default.
- W2884328272 hasRelatedWork W2124583046 @default.
- W2884328272 hasRelatedWork W2884328272 @default.
- W2884328272 hasRelatedWork W2963255279 @default.
- W2884328272 hasRelatedWork W3208051568 @default.
- W2884328272 hasRelatedWork W322134698 @default.
- W2884328272 isParatext "false" @default.
- W2884328272 isRetracted "false" @default.
- W2884328272 magId "2884328272" @default.
- W2884328272 workType "article" @default.