Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036407212> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3036407212 abstract "Artificial neural networks (ANNs) are commonly labelled as black-boxes, lacking interpretability. This hinders human understanding of ANNs' behaviors. A need exists to generate a meaningful sequential logic for the production of a specific output. Decision trees exhibit better interpretability and expressive power due to their representation language and the existence of efficient algorithms to generate rules. Growing a decision tree based on the available data could produce larger than necessary trees or trees that do not generalise well. In this paper, we introduce two novel multivariate decision tree (MDT) algorithms for rule extraction from an ANN: an Exact-Convertible Decision Tree (EC-DT) and an Extended C-Net algorithm to transform a neural network with Rectified Linear Unit activation functions into a representative tree which can be used to extract multivariate rules for reasoning. While the EC-DT translates the ANN in a layer-wise manner to represent exactly the decision boundaries implicitlylearned by the hidden layers of the network, the Extended C-Net inherits the decompositional approach from EC-DT and combines with a C5 tree learning algorithm to construct the decision rules. The results suggest that while EC-DT is superior in preserving the structure and the accuracy of ANN, Extended C-Net generates the most compact and highly effective trees from ANN. Both proposed MDT algorithms generate rules including combinations of multiple attributes for precise interpretation of decision-making processes." @default.
- W3036407212 created "2020-06-25" @default.
- W3036407212 creator A5022974795 @default.
- W3036407212 creator A5042524342 @default.
- W3036407212 creator A5047705901 @default.
- W3036407212 date "2020-03-10" @default.
- W3036407212 modified "2023-09-27" @default.
- W3036407212 title "An Exact Transformation from Deep Neural Networks to Multi-Class Multivariate Decision Trees" @default.
- W3036407212 hasPublicationYear "2020" @default.
- W3036407212 type Work @default.
- W3036407212 sameAs 3036407212 @default.
- W3036407212 citedByCount "0" @default.
- W3036407212 crossrefType "posted-content" @default.
- W3036407212 hasAuthorship W3036407212A5022974795 @default.
- W3036407212 hasAuthorship W3036407212A5042524342 @default.
- W3036407212 hasAuthorship W3036407212A5047705901 @default.
- W3036407212 hasConcept C10229987 @default.
- W3036407212 hasConcept C104317684 @default.
- W3036407212 hasConcept C113174947 @default.
- W3036407212 hasConcept C11413529 @default.
- W3036407212 hasConcept C119857082 @default.
- W3036407212 hasConcept C124101348 @default.
- W3036407212 hasConcept C134306372 @default.
- W3036407212 hasConcept C154945302 @default.
- W3036407212 hasConcept C183931066 @default.
- W3036407212 hasConcept C185592680 @default.
- W3036407212 hasConcept C204241405 @default.
- W3036407212 hasConcept C2781067378 @default.
- W3036407212 hasConcept C33923547 @default.
- W3036407212 hasConcept C41008148 @default.
- W3036407212 hasConcept C50644808 @default.
- W3036407212 hasConcept C5481197 @default.
- W3036407212 hasConcept C55493867 @default.
- W3036407212 hasConcept C84525736 @default.
- W3036407212 hasConceptScore W3036407212C10229987 @default.
- W3036407212 hasConceptScore W3036407212C104317684 @default.
- W3036407212 hasConceptScore W3036407212C113174947 @default.
- W3036407212 hasConceptScore W3036407212C11413529 @default.
- W3036407212 hasConceptScore W3036407212C119857082 @default.
- W3036407212 hasConceptScore W3036407212C124101348 @default.
- W3036407212 hasConceptScore W3036407212C134306372 @default.
- W3036407212 hasConceptScore W3036407212C154945302 @default.
- W3036407212 hasConceptScore W3036407212C183931066 @default.
- W3036407212 hasConceptScore W3036407212C185592680 @default.
- W3036407212 hasConceptScore W3036407212C204241405 @default.
- W3036407212 hasConceptScore W3036407212C2781067378 @default.
- W3036407212 hasConceptScore W3036407212C33923547 @default.
- W3036407212 hasConceptScore W3036407212C41008148 @default.
- W3036407212 hasConceptScore W3036407212C50644808 @default.
- W3036407212 hasConceptScore W3036407212C5481197 @default.
- W3036407212 hasConceptScore W3036407212C55493867 @default.
- W3036407212 hasConceptScore W3036407212C84525736 @default.
- W3036407212 hasLocation W30364072121 @default.
- W3036407212 hasOpenAccess W3036407212 @default.
- W3036407212 hasPrimaryLocation W30364072121 @default.
- W3036407212 hasRelatedWork W153697471 @default.
- W3036407212 hasRelatedWork W1967387730 @default.
- W3036407212 hasRelatedWork W1979441003 @default.
- W3036407212 hasRelatedWork W2027445945 @default.
- W3036407212 hasRelatedWork W2063670896 @default.
- W3036407212 hasRelatedWork W2070970059 @default.
- W3036407212 hasRelatedWork W2123199310 @default.
- W3036407212 hasRelatedWork W2134004542 @default.
- W3036407212 hasRelatedWork W2137160483 @default.
- W3036407212 hasRelatedWork W2808986925 @default.
- W3036407212 hasRelatedWork W2902568440 @default.
- W3036407212 hasRelatedWork W2914539226 @default.
- W3036407212 hasRelatedWork W3012522983 @default.
- W3036407212 hasRelatedWork W3105989472 @default.
- W3036407212 hasRelatedWork W3124150752 @default.
- W3036407212 hasRelatedWork W3154228815 @default.
- W3036407212 hasRelatedWork W3200075121 @default.
- W3036407212 hasRelatedWork W3209012620 @default.
- W3036407212 hasRelatedWork W3212215016 @default.
- W3036407212 hasRelatedWork W3212464206 @default.
- W3036407212 isParatext "false" @default.
- W3036407212 isRetracted "false" @default.
- W3036407212 magId "3036407212" @default.
- W3036407212 workType "article" @default.