Matches in SemOpenAlex for { <https://semopenalex.org/work/W2959176945> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2959176945 abstract "Machine learning -- the part of artificial intelligence aimed at eliciting knowledge from data and automated decision making without explicit instructions -- is making great strides, with new algorithms being invented every day. These algorithms find myriads of applications, but their ubiquity often comes at the expense of limited interpretability, hidden biases and unexpected vulnerabilities. Whenever one of these factors is a priority, the learning algorithm of choice is often a method considered to be inherently interpretable, e.g. logical models such as decision trees. In my research I challenge this assumption and highlight (quite common) cases when the assumed interpretability fails to deliver. To restore interpretability of logical machine learning models (decision trees and their ensembles in particular) I propose to explain them with class-contrastive counterfactual statements, which are a very common type of explanation in human interactions, well-grounded in social science research. To evaluate transparency of such models I collate explainability desiderata that can be used to systematically assess and compare such methods as an addition to user studies. Given contrastive explanations, I investigate their influence on the model's security, in particular gaming and stealing the model. Finally, I evaluate model fairness, where I am interested in choosing the most fair model among all the models with equal performance." @default.
- W2959176945 created "2019-07-23" @default.
- W2959176945 creator A5083819794 @default.
- W2959176945 date "2019-01-27" @default.
- W2959176945 modified "2023-10-18" @default.
- W2959176945 title "Fairness, Accountability and Transparency in Artificial Intelligence" @default.
- W2959176945 cites W2053075547 @default.
- W2959176945 cites W2282821441 @default.
- W2959176945 cites W2963095307 @default.
- W2959176945 cites W3102161834 @default.
- W2959176945 cites W4289258088 @default.
- W2959176945 doi "https://doi.org/10.1145/3306618.3314316" @default.
- W2959176945 hasPublicationYear "2019" @default.
- W2959176945 type Work @default.
- W2959176945 sameAs 2959176945 @default.
- W2959176945 citedByCount "3" @default.
- W2959176945 countsByYear W29591769452019 @default.
- W2959176945 countsByYear W29591769452021 @default.
- W2959176945 countsByYear W29591769452023 @default.
- W2959176945 crossrefType "proceedings-article" @default.
- W2959176945 hasAuthorship W2959176945A5083819794 @default.
- W2959176945 hasConcept C108650721 @default.
- W2959176945 hasConcept C111472728 @default.
- W2959176945 hasConcept C119857082 @default.
- W2959176945 hasConcept C138885662 @default.
- W2959176945 hasConcept C154945302 @default.
- W2959176945 hasConcept C17744445 @default.
- W2959176945 hasConcept C199539241 @default.
- W2959176945 hasConcept C2522767166 @default.
- W2959176945 hasConcept C2776007630 @default.
- W2959176945 hasConcept C2780233690 @default.
- W2959176945 hasConcept C2781067378 @default.
- W2959176945 hasConcept C38652104 @default.
- W2959176945 hasConcept C41008148 @default.
- W2959176945 hasConcept C84525736 @default.
- W2959176945 hasConceptScore W2959176945C108650721 @default.
- W2959176945 hasConceptScore W2959176945C111472728 @default.
- W2959176945 hasConceptScore W2959176945C119857082 @default.
- W2959176945 hasConceptScore W2959176945C138885662 @default.
- W2959176945 hasConceptScore W2959176945C154945302 @default.
- W2959176945 hasConceptScore W2959176945C17744445 @default.
- W2959176945 hasConceptScore W2959176945C199539241 @default.
- W2959176945 hasConceptScore W2959176945C2522767166 @default.
- W2959176945 hasConceptScore W2959176945C2776007630 @default.
- W2959176945 hasConceptScore W2959176945C2780233690 @default.
- W2959176945 hasConceptScore W2959176945C2781067378 @default.
- W2959176945 hasConceptScore W2959176945C38652104 @default.
- W2959176945 hasConceptScore W2959176945C41008148 @default.
- W2959176945 hasConceptScore W2959176945C84525736 @default.
- W2959176945 hasFunder F4320334627 @default.
- W2959176945 hasLocation W29591769451 @default.
- W2959176945 hasOpenAccess W2959176945 @default.
- W2959176945 hasPrimaryLocation W29591769451 @default.
- W2959176945 hasRelatedWork W1863951150 @default.
- W2959176945 hasRelatedWork W2066431708 @default.
- W2959176945 hasRelatedWork W2905433371 @default.
- W2959176945 hasRelatedWork W2964449086 @default.
- W2959176945 hasRelatedWork W3199802296 @default.
- W2959176945 hasRelatedWork W3201448254 @default.
- W2959176945 hasRelatedWork W4286970243 @default.
- W2959176945 hasRelatedWork W4293151273 @default.
- W2959176945 hasRelatedWork W4310278675 @default.
- W2959176945 hasRelatedWork W4361193272 @default.
- W2959176945 isParatext "false" @default.
- W2959176945 isRetracted "false" @default.
- W2959176945 magId "2959176945" @default.
- W2959176945 workType "article" @default.