Matches in SemOpenAlex for { <https://semopenalex.org/work/W1964166287> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W1964166287 endingPage "117" @default.
- W1964166287 startingPage "87" @default.
- W1964166287 abstract "This report investigates evolution strategies (ESs, a subclass of evolutionary algorithms) as an alternative to gradient-based neural network training. Based on an empirical comparison of population- and gradient-based search, we derive hints for parameterization and draw conclusions about the usefulness of evolution strategies for this purpose. We will see that ESs can only compete with gradient-based search in the case of small problems and that ESs are good for training neural networks with a non-differentiable activation function. Insights into how evolution strategies behave in search spaces generated by neural networks are offered. Here, we see that for this class of objective functions, the dimensionality of the problem is critical. With increasing numbers of decision variables, the learning becomes more and more difficult for ESs, and an “efficient” parameterization becomes crucial." @default.
- W1964166287 created "2016-06-24" @default.
- W1964166287 creator A5065126222 @default.
- W1964166287 date "2002-01-01" @default.
- W1964166287 modified "2023-10-18" @default.
- W1964166287 title "A comparison of evolution strategies and backpropagation for neural network training" @default.
- W1964166287 cites W116062058 @default.
- W1964166287 cites W1556539685 @default.
- W1964166287 cites W1859663958 @default.
- W1964166287 cites W200738318 @default.
- W1964166287 cites W2090270852 @default.
- W1964166287 cites W2103575890 @default.
- W1964166287 cites W2103593133 @default.
- W1964166287 cites W2111956384 @default.
- W1964166287 doi "https://doi.org/10.1016/s0925-2312(01)00596-3" @default.
- W1964166287 hasPublicationYear "2002" @default.
- W1964166287 type Work @default.
- W1964166287 sameAs 1964166287 @default.
- W1964166287 citedByCount "69" @default.
- W1964166287 countsByYear W19641662872012 @default.
- W1964166287 countsByYear W19641662872013 @default.
- W1964166287 countsByYear W19641662872014 @default.
- W1964166287 countsByYear W19641662872015 @default.
- W1964166287 countsByYear W19641662872016 @default.
- W1964166287 countsByYear W19641662872019 @default.
- W1964166287 countsByYear W19641662872020 @default.
- W1964166287 countsByYear W19641662872021 @default.
- W1964166287 countsByYear W19641662872022 @default.
- W1964166287 countsByYear W19641662872023 @default.
- W1964166287 crossrefType "journal-article" @default.
- W1964166287 hasAuthorship W1964166287A5065126222 @default.
- W1964166287 hasConcept C111030470 @default.
- W1964166287 hasConcept C119857082 @default.
- W1964166287 hasConcept C126255220 @default.
- W1964166287 hasConcept C134306372 @default.
- W1964166287 hasConcept C14036430 @default.
- W1964166287 hasConcept C154945302 @default.
- W1964166287 hasConcept C155032097 @default.
- W1964166287 hasConcept C159149176 @default.
- W1964166287 hasConcept C202615002 @default.
- W1964166287 hasConcept C2777212361 @default.
- W1964166287 hasConcept C33923547 @default.
- W1964166287 hasConcept C41008148 @default.
- W1964166287 hasConcept C50644808 @default.
- W1964166287 hasConcept C78458016 @default.
- W1964166287 hasConcept C86803240 @default.
- W1964166287 hasConceptScore W1964166287C111030470 @default.
- W1964166287 hasConceptScore W1964166287C119857082 @default.
- W1964166287 hasConceptScore W1964166287C126255220 @default.
- W1964166287 hasConceptScore W1964166287C134306372 @default.
- W1964166287 hasConceptScore W1964166287C14036430 @default.
- W1964166287 hasConceptScore W1964166287C154945302 @default.
- W1964166287 hasConceptScore W1964166287C155032097 @default.
- W1964166287 hasConceptScore W1964166287C159149176 @default.
- W1964166287 hasConceptScore W1964166287C202615002 @default.
- W1964166287 hasConceptScore W1964166287C2777212361 @default.
- W1964166287 hasConceptScore W1964166287C33923547 @default.
- W1964166287 hasConceptScore W1964166287C41008148 @default.
- W1964166287 hasConceptScore W1964166287C50644808 @default.
- W1964166287 hasConceptScore W1964166287C78458016 @default.
- W1964166287 hasConceptScore W1964166287C86803240 @default.
- W1964166287 hasIssue "1-4" @default.
- W1964166287 hasLocation W19641662871 @default.
- W1964166287 hasOpenAccess W1964166287 @default.
- W1964166287 hasPrimaryLocation W19641662871 @default.
- W1964166287 hasRelatedWork W1495379181 @default.
- W1964166287 hasRelatedWork W2157746493 @default.
- W1964166287 hasRelatedWork W2193130317 @default.
- W1964166287 hasRelatedWork W2792697259 @default.
- W1964166287 hasRelatedWork W2894173309 @default.
- W1964166287 hasRelatedWork W2948568013 @default.
- W1964166287 hasRelatedWork W2961085424 @default.
- W1964166287 hasRelatedWork W2970529185 @default.
- W1964166287 hasRelatedWork W3138179150 @default.
- W1964166287 hasRelatedWork W4206400463 @default.
- W1964166287 hasVolume "42" @default.
- W1964166287 isParatext "false" @default.
- W1964166287 isRetracted "false" @default.
- W1964166287 magId "1964166287" @default.
- W1964166287 workType "article" @default.