Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310429785> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4310429785 abstract "Tabular biomedical data is often high-dimensional but with a very small number of samples. Although recent work showed that well-regularised simple neural networks could outperform more sophisticated architectures on tabular data, they are still prone to overfitting on tiny datasets with many potentially irrelevant features. To combat these issues, we propose Weight Predictor Network with Feature Selection (WPFS) for learning neural networks from high-dimensional and small sample data by reducing the number of learnable parameters and simultaneously performing feature selection. In addition to the classification network, WPFS uses two small auxiliary networks that together output the weights of the first layer of the classification model. We evaluate on nine real-world biomedical datasets and demonstrate that WPFS outperforms other standard as well as more recent methods typically applied to tabular data. Furthermore, we investigate the proposed feature selection mechanism and show that it improves performance while providing useful insights into the learning task." @default.
- W4310429785 created "2022-12-10" @default.
- W4310429785 creator A5003682166 @default.
- W4310429785 creator A5036018012 @default.
- W4310429785 creator A5056748708 @default.
- W4310429785 creator A5090638800 @default.
- W4310429785 date "2022-11-28" @default.
- W4310429785 modified "2023-09-27" @default.
- W4310429785 title "Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data" @default.
- W4310429785 doi "https://doi.org/10.48550/arxiv.2211.15616" @default.
- W4310429785 hasPublicationYear "2022" @default.
- W4310429785 type Work @default.
- W4310429785 citedByCount "0" @default.
- W4310429785 crossrefType "posted-content" @default.
- W4310429785 hasAuthorship W4310429785A5003682166 @default.
- W4310429785 hasAuthorship W4310429785A5036018012 @default.
- W4310429785 hasAuthorship W4310429785A5056748708 @default.
- W4310429785 hasAuthorship W4310429785A5090638800 @default.
- W4310429785 hasBestOaLocation W43104297851 @default.
- W4310429785 hasConcept C119857082 @default.
- W4310429785 hasConcept C124101348 @default.
- W4310429785 hasConcept C127413603 @default.
- W4310429785 hasConcept C138885662 @default.
- W4310429785 hasConcept C148483581 @default.
- W4310429785 hasConcept C153180895 @default.
- W4310429785 hasConcept C154945302 @default.
- W4310429785 hasConcept C185592680 @default.
- W4310429785 hasConcept C198531522 @default.
- W4310429785 hasConcept C201995342 @default.
- W4310429785 hasConcept C22019652 @default.
- W4310429785 hasConcept C2776401178 @default.
- W4310429785 hasConcept C2780451532 @default.
- W4310429785 hasConcept C41008148 @default.
- W4310429785 hasConcept C41895202 @default.
- W4310429785 hasConcept C43617362 @default.
- W4310429785 hasConcept C50644808 @default.
- W4310429785 hasConcept C81917197 @default.
- W4310429785 hasConceptScore W4310429785C119857082 @default.
- W4310429785 hasConceptScore W4310429785C124101348 @default.
- W4310429785 hasConceptScore W4310429785C127413603 @default.
- W4310429785 hasConceptScore W4310429785C138885662 @default.
- W4310429785 hasConceptScore W4310429785C148483581 @default.
- W4310429785 hasConceptScore W4310429785C153180895 @default.
- W4310429785 hasConceptScore W4310429785C154945302 @default.
- W4310429785 hasConceptScore W4310429785C185592680 @default.
- W4310429785 hasConceptScore W4310429785C198531522 @default.
- W4310429785 hasConceptScore W4310429785C201995342 @default.
- W4310429785 hasConceptScore W4310429785C22019652 @default.
- W4310429785 hasConceptScore W4310429785C2776401178 @default.
- W4310429785 hasConceptScore W4310429785C2780451532 @default.
- W4310429785 hasConceptScore W4310429785C41008148 @default.
- W4310429785 hasConceptScore W4310429785C41895202 @default.
- W4310429785 hasConceptScore W4310429785C43617362 @default.
- W4310429785 hasConceptScore W4310429785C50644808 @default.
- W4310429785 hasConceptScore W4310429785C81917197 @default.
- W4310429785 hasLocation W43104297851 @default.
- W4310429785 hasLocation W43104297852 @default.
- W4310429785 hasOpenAccess W4310429785 @default.
- W4310429785 hasPrimaryLocation W43104297851 @default.
- W4310429785 hasRelatedWork W1996541855 @default.
- W4310429785 hasRelatedWork W2409149208 @default.
- W4310429785 hasRelatedWork W2767651786 @default.
- W4310429785 hasRelatedWork W2963373297 @default.
- W4310429785 hasRelatedWork W2989932438 @default.
- W4310429785 hasRelatedWork W3099765033 @default.
- W4310429785 hasRelatedWork W4200100536 @default.
- W4310429785 hasRelatedWork W4210794429 @default.
- W4310429785 hasRelatedWork W4283732135 @default.
- W4310429785 hasRelatedWork W4385743487 @default.
- W4310429785 isParatext "false" @default.
- W4310429785 isRetracted "false" @default.
- W4310429785 workType "article" @default.