Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387185301> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4387185301 abstract "Understanding the decision-making process of a machine/deep learning model is crucial, particularly in security-sensitive applications. In this study, we introduce a neural network framework that combines the global and exact interpretability properties of rule-based models with the high performance of deep neural networks. Our proposed framework, called Truth Table rules (TT-rules), is built upon Truth Table nets (TTnets), a family of deep neural networks initially developed for formal verification. By extracting the set of necessary and sufficient rules R from the trained TTnet model (global interpretability), yielding the same output as the TTnet (exact interpretability), TT-rules effectively transforms the neural network into a rule-based model. This rule-based model supports binary classification, multi-label classification, and regression tasks for tabular datasets. Furthermore, our TT-rules framework optimizes the rule set R into Ropt by reducing the number and size of the rules. To enhance model interpretation, we leverage Reduced Ordered Binary Decision Diagrams (ROBDDs) to visualize these rules effectively. After outlining the framework, we evaluate the performance of TT-rules on seven tabular datasets from finance, healthcare, and justice domains. We also compare the TT-rules framework to state-of-the-art rule-based methods. Our results demonstrate that TT-rules achieves equal or higher performance compared to other interpretable methods while maintaining a balance between performance and complexity. Notably, TT-rules presents the first accurate rule-based model capable of fitting large tabular datasets, including two real-life DNA datasets with over 20K features. Finally, we extensively investigate a rule-based model derived from TT-rules using the Adult dataset." @default.
- W4387185301 created "2023-09-30" @default.
- W4387185301 creator A5004490094 @default.
- W4387185301 creator A5012053340 @default.
- W4387185301 creator A5071655967 @default.
- W4387185301 creator A5092905602 @default.
- W4387185301 date "2023-09-28" @default.
- W4387185301 modified "2023-09-30" @default.
- W4387185301 title "Neural Network-Based Rule Models with Truth Tables" @default.
- W4387185301 doi "https://doi.org/10.3233/faia230274" @default.
- W4387185301 hasPublicationYear "2023" @default.
- W4387185301 type Work @default.
- W4387185301 citedByCount "0" @default.
- W4387185301 crossrefType "book-chapter" @default.
- W4387185301 hasAuthorship W4387185301A5004490094 @default.
- W4387185301 hasAuthorship W4387185301A5012053340 @default.
- W4387185301 hasAuthorship W4387185301A5071655967 @default.
- W4387185301 hasAuthorship W4387185301A5092905602 @default.
- W4387185301 hasBestOaLocation W43871853011 @default.
- W4387185301 hasConcept C119857082 @default.
- W4387185301 hasConcept C124101348 @default.
- W4387185301 hasConcept C149271511 @default.
- W4387185301 hasConcept C153083717 @default.
- W4387185301 hasConcept C154945302 @default.
- W4387185301 hasConcept C177264268 @default.
- W4387185301 hasConcept C199360897 @default.
- W4387185301 hasConcept C2781067378 @default.
- W4387185301 hasConcept C41008148 @default.
- W4387185301 hasConcept C50644808 @default.
- W4387185301 hasConceptScore W4387185301C119857082 @default.
- W4387185301 hasConceptScore W4387185301C124101348 @default.
- W4387185301 hasConceptScore W4387185301C149271511 @default.
- W4387185301 hasConceptScore W4387185301C153083717 @default.
- W4387185301 hasConceptScore W4387185301C154945302 @default.
- W4387185301 hasConceptScore W4387185301C177264268 @default.
- W4387185301 hasConceptScore W4387185301C199360897 @default.
- W4387185301 hasConceptScore W4387185301C2781067378 @default.
- W4387185301 hasConceptScore W4387185301C41008148 @default.
- W4387185301 hasConceptScore W4387185301C50644808 @default.
- W4387185301 hasLocation W43871853011 @default.
- W4387185301 hasOpenAccess W4387185301 @default.
- W4387185301 hasPrimaryLocation W43871853011 @default.
- W4387185301 hasRelatedWork W3006943036 @default.
- W4387185301 hasRelatedWork W3023163568 @default.
- W4387185301 hasRelatedWork W3136084287 @default.
- W4387185301 hasRelatedWork W4200511449 @default.
- W4387185301 hasRelatedWork W4206534706 @default.
- W4387185301 hasRelatedWork W4229079080 @default.
- W4387185301 hasRelatedWork W4299487748 @default.
- W4387185301 hasRelatedWork W4385957992 @default.
- W4387185301 hasRelatedWork W4385965371 @default.
- W4387185301 hasRelatedWork W4386025632 @default.
- W4387185301 isParatext "false" @default.
- W4387185301 isRetracted "false" @default.
- W4387185301 workType "book-chapter" @default.