Matches in SemOpenAlex for { <https://semopenalex.org/work/W3150767555> ?p ?o ?g. }
- W3150767555 endingPage "98" @default.
- W3150767555 startingPage "75" @default.
- W3150767555 abstract "We investigate the addition of constraints on the function image and its derivatives for the incorporation of prior knowledge in symbolic regression. The approach is called shape-constrained symbolic regression and allows us to enforce, for example, monotonicity of the function over selected inputs. The aim is to find models which conform to expected behavior and which have improved extrapolation capabilities. We demonstrate the feasibility of the idea and propose and compare two evolutionary algorithms for shape-constrained symbolic regression: (i) an extension of tree-based genetic programming which discards infeasible solutions in the selection step, and (ii) a two-population evolutionary algorithm that separates the feasible from the infeasible solutions. In both algorithms we use interval arithmetic to approximate bounds for models and their partial derivatives. The algorithms are tested on a set of 19 synthetic and four real-world regression problems. Both algorithms are able to identify models which conform to shape constraints which is not the case for the unmodified symbolic regression algorithms. However, the predictive accuracy of models with constraints is worse on the training set and the test set. Shape-constrained polynomial regression produces the best results for the test set but also significantly larger models." @default.
- W3150767555 created "2021-04-13" @default.
- W3150767555 creator A5004674296 @default.
- W3150767555 creator A5010769668 @default.
- W3150767555 creator A5019952173 @default.
- W3150767555 creator A5033231632 @default.
- W3150767555 creator A5071749418 @default.
- W3150767555 date "2022-01-01" @default.
- W3150767555 modified "2023-09-30" @default.
- W3150767555 title "Shape-Constrained Symbolic Regression—Improving Extrapolation with Prior Knowledge" @default.
- W3150767555 cites W117221855 @default.
- W3150767555 cites W121066256 @default.
- W3150767555 cites W1519072852 @default.
- W3150767555 cites W1795093649 @default.
- W3150767555 cites W1973385701 @default.
- W3150767555 cites W1974805999 @default.
- W3150767555 cites W1978467861 @default.
- W3150767555 cites W1979378106 @default.
- W3150767555 cites W199024138 @default.
- W3150767555 cites W2001466640 @default.
- W3150767555 cites W2030947209 @default.
- W3150767555 cites W2041091076 @default.
- W3150767555 cites W2059396387 @default.
- W3150767555 cites W2087512478 @default.
- W3150767555 cites W2120235997 @default.
- W3150767555 cites W2131480237 @default.
- W3150767555 cites W2149362532 @default.
- W3150767555 cites W2166140447 @default.
- W3150767555 cites W2296218809 @default.
- W3150767555 cites W2588072912 @default.
- W3150767555 cites W2735219249 @default.
- W3150767555 cites W2945976633 @default.
- W3150767555 cites W2954009196 @default.
- W3150767555 cites W2954765142 @default.
- W3150767555 cites W2963407939 @default.
- W3150767555 cites W2964239200 @default.
- W3150767555 cites W2967169354 @default.
- W3150767555 cites W2991933648 @default.
- W3150767555 cites W3016401366 @default.
- W3150767555 cites W3022177149 @default.
- W3150767555 cites W3111210983 @default.
- W3150767555 cites W4246840991 @default.
- W3150767555 cites W4289765664 @default.
- W3150767555 doi "https://doi.org/10.1162/evco_a_00294" @default.
- W3150767555 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34623432" @default.
- W3150767555 hasPublicationYear "2022" @default.
- W3150767555 type Work @default.
- W3150767555 sameAs 3150767555 @default.
- W3150767555 citedByCount "13" @default.
- W3150767555 countsByYear W31507675552021 @default.
- W3150767555 countsByYear W31507675552022 @default.
- W3150767555 countsByYear W31507675552023 @default.
- W3150767555 crossrefType "journal-article" @default.
- W3150767555 hasAuthorship W3150767555A5004674296 @default.
- W3150767555 hasAuthorship W3150767555A5010769668 @default.
- W3150767555 hasAuthorship W3150767555A5019952173 @default.
- W3150767555 hasAuthorship W3150767555A5033231632 @default.
- W3150767555 hasAuthorship W3150767555A5071749418 @default.
- W3150767555 hasBestOaLocation W31507675551 @default.
- W3150767555 hasConcept C105795698 @default.
- W3150767555 hasConcept C110332635 @default.
- W3150767555 hasConcept C11413529 @default.
- W3150767555 hasConcept C119857082 @default.
- W3150767555 hasConcept C120068334 @default.
- W3150767555 hasConcept C126255220 @default.
- W3150767555 hasConcept C132459708 @default.
- W3150767555 hasConcept C144024400 @default.
- W3150767555 hasConcept C149923435 @default.
- W3150767555 hasConcept C152877465 @default.
- W3150767555 hasConcept C154945302 @default.
- W3150767555 hasConcept C159149176 @default.
- W3150767555 hasConcept C169903167 @default.
- W3150767555 hasConcept C177264268 @default.
- W3150767555 hasConcept C199360897 @default.
- W3150767555 hasConcept C2776400721 @default.
- W3150767555 hasConcept C2908647359 @default.
- W3150767555 hasConcept C33923547 @default.
- W3150767555 hasConcept C41008148 @default.
- W3150767555 hasConcept C83546350 @default.
- W3150767555 hasConceptScore W3150767555C105795698 @default.
- W3150767555 hasConceptScore W3150767555C110332635 @default.
- W3150767555 hasConceptScore W3150767555C11413529 @default.
- W3150767555 hasConceptScore W3150767555C119857082 @default.
- W3150767555 hasConceptScore W3150767555C120068334 @default.
- W3150767555 hasConceptScore W3150767555C126255220 @default.
- W3150767555 hasConceptScore W3150767555C132459708 @default.
- W3150767555 hasConceptScore W3150767555C144024400 @default.
- W3150767555 hasConceptScore W3150767555C149923435 @default.
- W3150767555 hasConceptScore W3150767555C152877465 @default.
- W3150767555 hasConceptScore W3150767555C154945302 @default.
- W3150767555 hasConceptScore W3150767555C159149176 @default.
- W3150767555 hasConceptScore W3150767555C169903167 @default.
- W3150767555 hasConceptScore W3150767555C177264268 @default.
- W3150767555 hasConceptScore W3150767555C199360897 @default.
- W3150767555 hasConceptScore W3150767555C2776400721 @default.
- W3150767555 hasConceptScore W3150767555C2908647359 @default.
- W3150767555 hasConceptScore W3150767555C33923547 @default.
- W3150767555 hasConceptScore W3150767555C41008148 @default.