Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323362183> ?p ?o ?g. }
- W4323362183 endingPage "e1241" @default.
- W4323362183 startingPage "e1241" @default.
- W4323362183 abstract "There are many problems in physics, biology, and other natural sciences in which symbolic regression can provide valuable insights and discover new laws of nature. Widespread deep neural networks do not provide interpretable solutions. Meanwhile, symbolic expressions give us a clear relation between observations and the target variable. However, at the moment, there is no dominant solution for the symbolic regression task, and we aim to reduce this gap with our algorithm. In this work, we propose a novel deep learning framework for symbolic expression generation via variational autoencoder (VAE). We suggest using a VAE to generate mathematical expressions, and our training strategy forces generated formulas to fit a given dataset. Our framework allows encoding apriori knowledge of the formulas into fast-check predicates that speed up the optimization process. We compare our method to modern symbolic regression benchmarks and show that our method outperforms the competitors under noisy conditions. The recovery rate of SEGVAE is 65% on the Ngyuen dataset with a noise level of 10%, which is better than the previously reported SOTA by 20%. We demonstrate that this value depends on the dataset and can be even higher." @default.
- W4323362183 created "2023-03-08" @default.
- W4323362183 creator A5009922838 @default.
- W4323362183 creator A5029181198 @default.
- W4323362183 creator A5064894803 @default.
- W4323362183 creator A5066291963 @default.
- W4323362183 creator A5086986254 @default.
- W4323362183 date "2023-03-07" @default.
- W4323362183 modified "2023-10-01" @default.
- W4323362183 title "Symbolic expression generation <i>via</i> variational auto-encoder" @default.
- W4323362183 cites W1591435035 @default.
- W4323362183 cites W1979769287 @default.
- W4323362183 cites W2038659300 @default.
- W4323362183 cites W2040492000 @default.
- W4323362183 cites W2164655924 @default.
- W4323362183 cites W2884775584 @default.
- W4323362183 cites W2945570991 @default.
- W4323362183 cites W3016401366 @default.
- W4323362183 cites W3164124231 @default.
- W4323362183 cites W3172431719 @default.
- W4323362183 cites W4285108454 @default.
- W4323362183 cites W4286890432 @default.
- W4323362183 cites W4293471604 @default.
- W4323362183 cites W4311415873 @default.
- W4323362183 cites W4317438059 @default.
- W4323362183 doi "https://doi.org/10.7717/peerj-cs.1241" @default.
- W4323362183 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37346583" @default.
- W4323362183 hasPublicationYear "2023" @default.
- W4323362183 type Work @default.
- W4323362183 citedByCount "0" @default.
- W4323362183 crossrefType "journal-article" @default.
- W4323362183 hasAuthorship W4323362183A5009922838 @default.
- W4323362183 hasAuthorship W4323362183A5029181198 @default.
- W4323362183 hasAuthorship W4323362183A5064894803 @default.
- W4323362183 hasAuthorship W4323362183A5066291963 @default.
- W4323362183 hasAuthorship W4323362183A5086986254 @default.
- W4323362183 hasBestOaLocation W43233621831 @default.
- W4323362183 hasConcept C101738243 @default.
- W4323362183 hasConcept C105795698 @default.
- W4323362183 hasConcept C110332635 @default.
- W4323362183 hasConcept C111919701 @default.
- W4323362183 hasConcept C11413529 @default.
- W4323362183 hasConcept C118505674 @default.
- W4323362183 hasConcept C119857082 @default.
- W4323362183 hasConcept C124101348 @default.
- W4323362183 hasConcept C153180895 @default.
- W4323362183 hasConcept C154945302 @default.
- W4323362183 hasConcept C162324750 @default.
- W4323362183 hasConcept C187736073 @default.
- W4323362183 hasConcept C199360897 @default.
- W4323362183 hasConcept C25343380 @default.
- W4323362183 hasConcept C2776400721 @default.
- W4323362183 hasConcept C2780451532 @default.
- W4323362183 hasConcept C33923547 @default.
- W4323362183 hasConcept C41008148 @default.
- W4323362183 hasConcept C50644808 @default.
- W4323362183 hasConcept C83546350 @default.
- W4323362183 hasConcept C90559484 @default.
- W4323362183 hasConceptScore W4323362183C101738243 @default.
- W4323362183 hasConceptScore W4323362183C105795698 @default.
- W4323362183 hasConceptScore W4323362183C110332635 @default.
- W4323362183 hasConceptScore W4323362183C111919701 @default.
- W4323362183 hasConceptScore W4323362183C11413529 @default.
- W4323362183 hasConceptScore W4323362183C118505674 @default.
- W4323362183 hasConceptScore W4323362183C119857082 @default.
- W4323362183 hasConceptScore W4323362183C124101348 @default.
- W4323362183 hasConceptScore W4323362183C153180895 @default.
- W4323362183 hasConceptScore W4323362183C154945302 @default.
- W4323362183 hasConceptScore W4323362183C162324750 @default.
- W4323362183 hasConceptScore W4323362183C187736073 @default.
- W4323362183 hasConceptScore W4323362183C199360897 @default.
- W4323362183 hasConceptScore W4323362183C25343380 @default.
- W4323362183 hasConceptScore W4323362183C2776400721 @default.
- W4323362183 hasConceptScore W4323362183C2780451532 @default.
- W4323362183 hasConceptScore W4323362183C33923547 @default.
- W4323362183 hasConceptScore W4323362183C41008148 @default.
- W4323362183 hasConceptScore W4323362183C50644808 @default.
- W4323362183 hasConceptScore W4323362183C83546350 @default.
- W4323362183 hasConceptScore W4323362183C90559484 @default.
- W4323362183 hasFunder F4320319755 @default.
- W4323362183 hasFunder F4320324261 @default.
- W4323362183 hasLocation W43233621831 @default.
- W4323362183 hasLocation W43233621832 @default.
- W4323362183 hasLocation W43233621833 @default.
- W4323362183 hasLocation W43233621834 @default.
- W4323362183 hasOpenAccess W4323362183 @default.
- W4323362183 hasPrimaryLocation W43233621831 @default.
- W4323362183 hasRelatedWork W2292254049 @default.
- W4323362183 hasRelatedWork W2592385986 @default.
- W4323362183 hasRelatedWork W2610906757 @default.
- W4323362183 hasRelatedWork W2772780115 @default.
- W4323362183 hasRelatedWork W2897995864 @default.
- W4323362183 hasRelatedWork W2998168123 @default.
- W4323362183 hasRelatedWork W3099179464 @default.
- W4323362183 hasRelatedWork W4281924768 @default.
- W4323362183 hasRelatedWork W4287995534 @default.
- W4323362183 hasRelatedWork W4309838615 @default.
- W4323362183 hasVolume "9" @default.