Matches in SemOpenAlex for { <https://semopenalex.org/work/W3112857588> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3112857588 abstract "In this paper we introduce the DMR – a prototype-based method and network architecture for deep learning which is using a decision tree (DT)- based inference and synthetic data to balance the classes. It builds upon the recently introduced xDNN method addressing more complex multi-class problems, specifically when classes are highly imbalanced. DMR moves away from a direct decision based on all classes towards a layered DT of pair-wise class comparisons. In addition, it forces the prototypes to be balanced between classes regardless of possible class imbalances of the training data. It has two novel mechanisms, namely i) using a DT to determine the winning class label, and ii) balancing the classes by synthesizing data around the prototypes determined from the available training data. As a result, we improved significantly the performance of the resulting fully explainable DNN as evidenced on the well know benchmark problem Caltech-101. Furthermore, we also achieved high results in terms of accuracy for the well known Caltech-256 dataset, as well as surpassed the results of other approaches on Faces-1999 problem. In summary, we propose a new approach specifically advantageous for imbalanced multi-class problems on well known hard benchmark datasets. Moreover, DMR offers full explainability, does not require GPUs and can continue to learn from new data by adding new prototypes preserving the previous ones but not requiring full retraining." @default.
- W3112857588 created "2020-12-21" @default.
- W3112857588 creator A5039480864 @default.
- W3112857588 creator A5068590850 @default.
- W3112857588 date "2020-10-11" @default.
- W3112857588 modified "2023-09-24" @default.
- W3112857588 title "Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference" @default.
- W3112857588 cites W1596717185 @default.
- W3112857588 cites W2017719567 @default.
- W3112857588 cites W2035883480 @default.
- W3112857588 cites W2097117768 @default.
- W3112857588 cites W2099085757 @default.
- W3112857588 cites W2108598243 @default.
- W3112857588 cites W2109255472 @default.
- W3112857588 cites W2140093718 @default.
- W3112857588 cites W2158247472 @default.
- W3112857588 cites W2194775991 @default.
- W3112857588 cites W2574388714 @default.
- W3112857588 cites W2896732351 @default.
- W3112857588 cites W2929291387 @default.
- W3112857588 cites W2964350391 @default.
- W3112857588 cites W3007204104 @default.
- W3112857588 cites W3021933602 @default.
- W3112857588 cites W3033988828 @default.
- W3112857588 cites W3041378136 @default.
- W3112857588 cites W4250859275 @default.
- W3112857588 doi "https://doi.org/10.1109/smc42975.2020.9282812" @default.
- W3112857588 hasPublicationYear "2020" @default.
- W3112857588 type Work @default.
- W3112857588 sameAs 3112857588 @default.
- W3112857588 citedByCount "9" @default.
- W3112857588 countsByYear W31128575882021 @default.
- W3112857588 countsByYear W31128575882022 @default.
- W3112857588 countsByYear W31128575882023 @default.
- W3112857588 crossrefType "proceedings-article" @default.
- W3112857588 hasAuthorship W3112857588A5039480864 @default.
- W3112857588 hasAuthorship W3112857588A5068590850 @default.
- W3112857588 hasBestOaLocation W31128575882 @default.
- W3112857588 hasConcept C113174947 @default.
- W3112857588 hasConcept C119857082 @default.
- W3112857588 hasConcept C134306372 @default.
- W3112857588 hasConcept C154945302 @default.
- W3112857588 hasConcept C161301231 @default.
- W3112857588 hasConcept C2776214188 @default.
- W3112857588 hasConcept C33923547 @default.
- W3112857588 hasConcept C37335422 @default.
- W3112857588 hasConcept C41008148 @default.
- W3112857588 hasConcept C50644808 @default.
- W3112857588 hasConcept C84525736 @default.
- W3112857588 hasConcept C86827895 @default.
- W3112857588 hasConceptScore W3112857588C113174947 @default.
- W3112857588 hasConceptScore W3112857588C119857082 @default.
- W3112857588 hasConceptScore W3112857588C134306372 @default.
- W3112857588 hasConceptScore W3112857588C154945302 @default.
- W3112857588 hasConceptScore W3112857588C161301231 @default.
- W3112857588 hasConceptScore W3112857588C2776214188 @default.
- W3112857588 hasConceptScore W3112857588C33923547 @default.
- W3112857588 hasConceptScore W3112857588C37335422 @default.
- W3112857588 hasConceptScore W3112857588C41008148 @default.
- W3112857588 hasConceptScore W3112857588C50644808 @default.
- W3112857588 hasConceptScore W3112857588C84525736 @default.
- W3112857588 hasConceptScore W3112857588C86827895 @default.
- W3112857588 hasLocation W31128575881 @default.
- W3112857588 hasLocation W31128575882 @default.
- W3112857588 hasLocation W31128575883 @default.
- W3112857588 hasOpenAccess W3112857588 @default.
- W3112857588 hasPrimaryLocation W31128575881 @default.
- W3112857588 hasRelatedWork W1470425429 @default.
- W3112857588 hasRelatedWork W3112857588 @default.
- W3112857588 hasRelatedWork W3200719183 @default.
- W3112857588 hasRelatedWork W3210877509 @default.
- W3112857588 hasRelatedWork W4205478082 @default.
- W3112857588 hasRelatedWork W4205958290 @default.
- W3112857588 hasRelatedWork W4249746146 @default.
- W3112857588 hasRelatedWork W4283016678 @default.
- W3112857588 hasRelatedWork W4306321456 @default.
- W3112857588 hasRelatedWork W4318350883 @default.
- W3112857588 isParatext "false" @default.
- W3112857588 isRetracted "false" @default.
- W3112857588 magId "3112857588" @default.
- W3112857588 workType "article" @default.