Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295678659> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4295678659 endingPage "40" @default.
- W4295678659 startingPage "1" @default.
- W4295678659 abstract "Genetic programming (GP), for the synthesis of brand new programs, continues to demonstrate increasingly capable results towards increasingly complex problems. A key challenge in GP is how to learn from the past so that the successful synthesis of simple programs can feed into more challenging unsolved problems. Transfer Learning (TL) in the literature has yet to demonstrate an automated mechanism to identify existing donor programs with high-utility genetic material for new problems, instead relying on human guidance. In this article we present a transfer learning mechanism for GP which fills this gap: we use a Turing-complete language for synthesis, and demonstrate how a neural network (NN) can be used to guide automated code fragment extraction from previously solved problems for injection into future problems. Using a framework which synthesises code from just 10 input-output examples, we first study NN ability to recognise the presence of code fragments in a larger program, then present an end-to-end system which takes only input-output examples and generates code fragments as it solves easier problems, then deploys selected high-utility fragments to solve harder ones. The use of NN-guided genetic material selection shows significant performance increases, on average doubling the percentage of programs that can be successfully synthesised when tested on two different problem corpora, compared with a non-transfer-learning GP baseline." @default.
- W4295678659 created "2022-09-14" @default.
- W4295678659 creator A5052240354 @default.
- W4295678659 creator A5079160321 @default.
- W4295678659 date "2022-11-24" @default.
- W4295678659 modified "2023-09-24" @default.
- W4295678659 title "Multi-donor Neural Transfer Learning for Genetic Programming" @default.
- W4295678659 cites W1523457267 @default.
- W4295678659 cites W1978661986 @default.
- W4295678659 cites W1990320219 @default.
- W4295678659 cites W2001496424 @default.
- W4295678659 cites W2031794118 @default.
- W4295678659 cites W2101432564 @default.
- W4295678659 cites W2114580749 @default.
- W4295678659 cites W2119240672 @default.
- W4295678659 cites W2120033649 @default.
- W4295678659 cites W2620845889 @default.
- W4295678659 cites W2725100189 @default.
- W4295678659 cites W2765557598 @default.
- W4295678659 cites W2807847220 @default.
- W4295678659 cites W2889097048 @default.
- W4295678659 cites W2947704387 @default.
- W4295678659 cites W2954281913 @default.
- W4295678659 cites W2954644321 @default.
- W4295678659 cites W2955973312 @default.
- W4295678659 cites W2959259755 @default.
- W4295678659 cites W2982960219 @default.
- W4295678659 cites W3006921505 @default.
- W4295678659 cites W3039553503 @default.
- W4295678659 cites W3042713055 @default.
- W4295678659 cites W3102501010 @default.
- W4295678659 cites W3106067791 @default.
- W4295678659 cites W4211119117 @default.
- W4295678659 cites W4240339708 @default.
- W4295678659 cites W2115185371 @default.
- W4295678659 doi "https://doi.org/10.1145/3563043" @default.
- W4295678659 hasPublicationYear "2022" @default.
- W4295678659 type Work @default.
- W4295678659 citedByCount "0" @default.
- W4295678659 crossrefType "journal-article" @default.
- W4295678659 hasAuthorship W4295678659A5052240354 @default.
- W4295678659 hasAuthorship W4295678659A5079160321 @default.
- W4295678659 hasBestOaLocation W42956786592 @default.
- W4295678659 hasConcept C110332635 @default.
- W4295678659 hasConcept C119857082 @default.
- W4295678659 hasConcept C150899416 @default.
- W4295678659 hasConcept C154945302 @default.
- W4295678659 hasConcept C173608175 @default.
- W4295678659 hasConcept C177264268 @default.
- W4295678659 hasConcept C199360897 @default.
- W4295678659 hasConcept C2776175482 @default.
- W4295678659 hasConcept C2776760102 @default.
- W4295678659 hasConcept C41008148 @default.
- W4295678659 hasConcept C50644808 @default.
- W4295678659 hasConcept C81917197 @default.
- W4295678659 hasConcept C8880873 @default.
- W4295678659 hasConcept C9870796 @default.
- W4295678659 hasConceptScore W4295678659C110332635 @default.
- W4295678659 hasConceptScore W4295678659C119857082 @default.
- W4295678659 hasConceptScore W4295678659C150899416 @default.
- W4295678659 hasConceptScore W4295678659C154945302 @default.
- W4295678659 hasConceptScore W4295678659C173608175 @default.
- W4295678659 hasConceptScore W4295678659C177264268 @default.
- W4295678659 hasConceptScore W4295678659C199360897 @default.
- W4295678659 hasConceptScore W4295678659C2776175482 @default.
- W4295678659 hasConceptScore W4295678659C2776760102 @default.
- W4295678659 hasConceptScore W4295678659C41008148 @default.
- W4295678659 hasConceptScore W4295678659C50644808 @default.
- W4295678659 hasConceptScore W4295678659C81917197 @default.
- W4295678659 hasConceptScore W4295678659C8880873 @default.
- W4295678659 hasConceptScore W4295678659C9870796 @default.
- W4295678659 hasIssue "4" @default.
- W4295678659 hasLocation W42956786591 @default.
- W4295678659 hasLocation W42956786592 @default.
- W4295678659 hasOpenAccess W4295678659 @default.
- W4295678659 hasPrimaryLocation W42956786591 @default.
- W4295678659 hasRelatedWork W2384847609 @default.
- W4295678659 hasRelatedWork W2960456850 @default.
- W4295678659 hasRelatedWork W3131673289 @default.
- W4295678659 hasRelatedWork W4281382123 @default.
- W4295678659 hasRelatedWork W4281645081 @default.
- W4295678659 hasRelatedWork W4295678659 @default.
- W4295678659 hasRelatedWork W4308262314 @default.
- W4295678659 hasRelatedWork W4318834068 @default.
- W4295678659 hasRelatedWork W4318957922 @default.
- W4295678659 hasRelatedWork W1629725936 @default.
- W4295678659 hasVolume "2" @default.
- W4295678659 isParatext "false" @default.
- W4295678659 isRetracted "false" @default.
- W4295678659 workType "article" @default.