Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289751514> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4289751514 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.
- W4289751514 created "2022-08-04" @default.
- W4289751514 creator A5044702596 @default.
- W4289751514 creator A5074202796 @default.
- W4289751514 creator A5090040051 @default.
- W4289751514 date "2018-07-20" @default.
- W4289751514 modified "2023-10-16" @default.
- W4289751514 title "Multi-criteria Evolution of Neural Network Topologies: Balancing Experience and Performance in Autonomous Systems" @default.
- W4289751514 doi "https://doi.org/10.48550/arxiv.1807.07979" @default.
- W4289751514 hasPublicationYear "2018" @default.
- W4289751514 type Work @default.
- W4289751514 citedByCount "0" @default.
- W4289751514 crossrefType "posted-content" @default.
- W4289751514 hasAuthorship W4289751514A5044702596 @default.
- W4289751514 hasAuthorship W4289751514A5074202796 @default.
- W4289751514 hasAuthorship W4289751514A5090040051 @default.
- W4289751514 hasBestOaLocation W42897515141 @default.
- W4289751514 hasConcept C111919701 @default.
- W4289751514 hasConcept C119599485 @default.
- W4289751514 hasConcept C120314980 @default.
- W4289751514 hasConcept C126255220 @default.
- W4289751514 hasConcept C127413603 @default.
- W4289751514 hasConcept C154945302 @default.
- W4289751514 hasConcept C159149176 @default.
- W4289751514 hasConcept C184720557 @default.
- W4289751514 hasConcept C199360897 @default.
- W4289751514 hasConcept C199845137 @default.
- W4289751514 hasConcept C207002847 @default.
- W4289751514 hasConcept C22019652 @default.
- W4289751514 hasConcept C26713055 @default.
- W4289751514 hasConcept C2776330181 @default.
- W4289751514 hasConcept C33923547 @default.
- W4289751514 hasConcept C41008148 @default.
- W4289751514 hasConcept C50644808 @default.
- W4289751514 hasConcept C63000827 @default.
- W4289751514 hasConceptScore W4289751514C111919701 @default.
- W4289751514 hasConceptScore W4289751514C119599485 @default.
- W4289751514 hasConceptScore W4289751514C120314980 @default.
- W4289751514 hasConceptScore W4289751514C126255220 @default.
- W4289751514 hasConceptScore W4289751514C127413603 @default.
- W4289751514 hasConceptScore W4289751514C154945302 @default.
- W4289751514 hasConceptScore W4289751514C159149176 @default.
- W4289751514 hasConceptScore W4289751514C184720557 @default.
- W4289751514 hasConceptScore W4289751514C199360897 @default.
- W4289751514 hasConceptScore W4289751514C199845137 @default.
- W4289751514 hasConceptScore W4289751514C207002847 @default.
- W4289751514 hasConceptScore W4289751514C22019652 @default.
- W4289751514 hasConceptScore W4289751514C26713055 @default.
- W4289751514 hasConceptScore W4289751514C2776330181 @default.
- W4289751514 hasConceptScore W4289751514C33923547 @default.
- W4289751514 hasConceptScore W4289751514C41008148 @default.
- W4289751514 hasConceptScore W4289751514C50644808 @default.
- W4289751514 hasConceptScore W4289751514C63000827 @default.
- W4289751514 hasLocation W42897515141 @default.
- W4289751514 hasOpenAccess W4289751514 @default.
- W4289751514 hasPrimaryLocation W42897515141 @default.
- W4289751514 hasRelatedWork W1517479908 @default.
- W4289751514 hasRelatedWork W1561327184 @default.
- W4289751514 hasRelatedWork W1709312490 @default.
- W4289751514 hasRelatedWork W2370129413 @default.
- W4289751514 hasRelatedWork W2543192342 @default.
- W4289751514 hasRelatedWork W2558510614 @default.
- W4289751514 hasRelatedWork W2784803070 @default.
- W4289751514 hasRelatedWork W2977596624 @default.
- W4289751514 hasRelatedWork W2182170470 @default.
- W4289751514 hasRelatedWork W2794878329 @default.
- W4289751514 isParatext "false" @default.
- W4289751514 isRetracted "false" @default.
- W4289751514 workType "article" @default.