Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313532332> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4313532332 abstract "Models can have different outcomes based on the different types of inputs; the training data used to build the model will change its output (a data-centric outcome), while the hyperparameter selection can also affect the model’s output and performance (a model-centric outcome). When building classification models, data scientists generally focus on model performance as the key metric, often focusing on accuracy. However, other metrics should be considered during model development that assesses performance in other ways, like fairness. Assessing the fairness during the model development process is often overlooked but should be considered as part of a model’s full assessment before deployment. This research investigates the fairness–accuracy tradeoff that occurred by changing only one hyperparameter in a neural network for binary classification to assess how this single change in the hidden layer can alter the algorithm’s accuracy and fairness. Neural networks were used for this assessment because of their wide usage across domains, limitations to current bias measurement methods, and the underlying challenges in their interpretability. Findings suggest that assessing accuracy and fairness during model development provides value while mitigating potential negative effects for users while reducing organizational risk. No particular activation function was found to be fairer than another. Notable differences in the fairness and accuracy measures could help developers deploy a model with high accuracy and robust fairness. Algorithm development should include a grid search for hyperparameter optimization that includes fairness along with performance measures, like accuracy. While the actual choices for hyperparameters may depend on the business context and dataset considered, an optimal development process should use both fairness and model performance metrics." @default.
- W4313532332 created "2023-01-06" @default.
- W4313532332 creator A5052307511 @default.
- W4313532332 creator A5079242586 @default.
- W4313532332 date "2023-01-03" @default.
- W4313532332 modified "2023-10-16" @default.
- W4313532332 title "Fairness–accuracy tradeoff: activation function choice in a neural network" @default.
- W4313532332 cites W1607120026 @default.
- W4313532332 cites W3004619146 @default.
- W4313532332 cites W3007844454 @default.
- W4313532332 cites W3035026192 @default.
- W4313532332 cites W3045233820 @default.
- W4313532332 cites W3094739916 @default.
- W4313532332 cites W3104114204 @default.
- W4313532332 cites W3111248923 @default.
- W4313532332 cites W3131567681 @default.
- W4313532332 cites W3168830259 @default.
- W4313532332 cites W3194668998 @default.
- W4313532332 cites W4206323856 @default.
- W4313532332 cites W4213313560 @default.
- W4313532332 cites W4220699706 @default.
- W4313532332 cites W4283076847 @default.
- W4313532332 doi "https://doi.org/10.1007/s43681-022-00250-9" @default.
- W4313532332 hasPublicationYear "2023" @default.
- W4313532332 type Work @default.
- W4313532332 citedByCount "0" @default.
- W4313532332 crossrefType "journal-article" @default.
- W4313532332 hasAuthorship W4313532332A5052307511 @default.
- W4313532332 hasAuthorship W4313532332A5079242586 @default.
- W4313532332 hasBestOaLocation W43135323321 @default.
- W4313532332 hasConcept C10485038 @default.
- W4313532332 hasConcept C119857082 @default.
- W4313532332 hasConcept C12267149 @default.
- W4313532332 hasConcept C124101348 @default.
- W4313532332 hasConcept C14036430 @default.
- W4313532332 hasConcept C144237770 @default.
- W4313532332 hasConcept C148220186 @default.
- W4313532332 hasConcept C154945302 @default.
- W4313532332 hasConcept C162324750 @default.
- W4313532332 hasConcept C176217482 @default.
- W4313532332 hasConcept C187736073 @default.
- W4313532332 hasConcept C21547014 @default.
- W4313532332 hasConcept C2780898871 @default.
- W4313532332 hasConcept C2781067378 @default.
- W4313532332 hasConcept C33923547 @default.
- W4313532332 hasConcept C41008148 @default.
- W4313532332 hasConcept C50644808 @default.
- W4313532332 hasConcept C78458016 @default.
- W4313532332 hasConcept C8642999 @default.
- W4313532332 hasConcept C86803240 @default.
- W4313532332 hasConceptScore W4313532332C10485038 @default.
- W4313532332 hasConceptScore W4313532332C119857082 @default.
- W4313532332 hasConceptScore W4313532332C12267149 @default.
- W4313532332 hasConceptScore W4313532332C124101348 @default.
- W4313532332 hasConceptScore W4313532332C14036430 @default.
- W4313532332 hasConceptScore W4313532332C144237770 @default.
- W4313532332 hasConceptScore W4313532332C148220186 @default.
- W4313532332 hasConceptScore W4313532332C154945302 @default.
- W4313532332 hasConceptScore W4313532332C162324750 @default.
- W4313532332 hasConceptScore W4313532332C176217482 @default.
- W4313532332 hasConceptScore W4313532332C187736073 @default.
- W4313532332 hasConceptScore W4313532332C21547014 @default.
- W4313532332 hasConceptScore W4313532332C2780898871 @default.
- W4313532332 hasConceptScore W4313532332C2781067378 @default.
- W4313532332 hasConceptScore W4313532332C33923547 @default.
- W4313532332 hasConceptScore W4313532332C41008148 @default.
- W4313532332 hasConceptScore W4313532332C50644808 @default.
- W4313532332 hasConceptScore W4313532332C78458016 @default.
- W4313532332 hasConceptScore W4313532332C8642999 @default.
- W4313532332 hasConceptScore W4313532332C86803240 @default.
- W4313532332 hasLocation W43135323321 @default.
- W4313532332 hasOpenAccess W4313532332 @default.
- W4313532332 hasPrimaryLocation W43135323321 @default.
- W4313532332 hasRelatedWork W3014750173 @default.
- W4313532332 hasRelatedWork W3139241485 @default.
- W4313532332 hasRelatedWork W3199608561 @default.
- W4313532332 hasRelatedWork W4281646320 @default.
- W4313532332 hasRelatedWork W4283697347 @default.
- W4313532332 hasRelatedWork W4287818966 @default.
- W4313532332 hasRelatedWork W4295309597 @default.
- W4313532332 hasRelatedWork W4298144215 @default.
- W4313532332 hasRelatedWork W4360764167 @default.
- W4313532332 hasRelatedWork W4381737452 @default.
- W4313532332 isParatext "false" @default.
- W4313532332 isRetracted "false" @default.
- W4313532332 workType "article" @default.