Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384388111> ?p ?o ?g. }
- W4384388111 abstract "Abstract The adoption of convolutional neural network (CNN) models in high-stake domains is hindered by their inability to meet society’s demand for transparency in decision-making. So far, a growing number of methodologies have emerged for developing CNN models that are interpretable by design. However, such models are not capable of providing interpretations in accordance with human perception, while maintaining competent performance. In this paper, we tackle these challenges with a novel, general framework for instantiating inherently interpretable CNN models, named E pluribus unum interpretable CNN (EPU-CNN). An EPU-CNN model consists of CNN sub-networks, each of which receives a different representation of an input image expressing a perceptual feature, such as color or texture. The output of an EPU-CNN model consists of the classification prediction and its interpretation, in terms of relative contributions of perceptual features in different regions of the input image. EPU-CNN models have been extensively evaluated on various publicly available datasets, as well as a contributed benchmark dataset. Medical datasets are used to demonstrate the applicability of EPU-CNN for risk-sensitive decisions in medicine. The experimental results indicate that EPU-CNN models can achieve a comparable or better classification performance than other CNN architectures while providing humanly perceivable interpretations." @default.
- W4384388111 created "2023-07-15" @default.
- W4384388111 creator A5020655974 @default.
- W4384388111 creator A5032958131 @default.
- W4384388111 creator A5042655412 @default.
- W4384388111 date "2023-07-14" @default.
- W4384388111 modified "2023-10-17" @default.
- W4384388111 title "E pluribus unum interpretable convolutional neural networks" @default.
- W4384388111 cites W1967199668 @default.
- W4384388111 cites W1980301542 @default.
- W4384388111 cites W1996929001 @default.
- W4384388111 cites W2000674655 @default.
- W4384388111 cites W2003834444 @default.
- W4384388111 cites W2033133413 @default.
- W4384388111 cites W2038705219 @default.
- W4384388111 cites W2041345388 @default.
- W4384388111 cites W2052985536 @default.
- W4384388111 cites W2055237367 @default.
- W4384388111 cites W2117432840 @default.
- W4384388111 cites W2119429959 @default.
- W4384388111 cites W2123402141 @default.
- W4384388111 cites W2132725786 @default.
- W4384388111 cites W2147256718 @default.
- W4384388111 cites W2157355630 @default.
- W4384388111 cites W2194775991 @default.
- W4384388111 cites W2282821441 @default.
- W4384388111 cites W2367397349 @default.
- W4384388111 cites W2620841913 @default.
- W4384388111 cites W2623808523 @default.
- W4384388111 cites W2764024122 @default.
- W4384388111 cites W2803469628 @default.
- W4384388111 cites W28412257 @default.
- W4384388111 cites W2898694742 @default.
- W4384388111 cites W2910705748 @default.
- W4384388111 cites W2945976633 @default.
- W4384388111 cites W2962858109 @default.
- W4384388111 cites W2963446712 @default.
- W4384388111 cites W2963749936 @default.
- W4384388111 cites W2969364300 @default.
- W4384388111 cites W2969880113 @default.
- W4384388111 cites W2979316730 @default.
- W4384388111 cites W2979997102 @default.
- W4384388111 cites W2981731882 @default.
- W4384388111 cites W3010143093 @default.
- W4384388111 cites W3028574926 @default.
- W4384388111 cites W3033901474 @default.
- W4384388111 cites W3105753517 @default.
- W4384388111 cites W3106638601 @default.
- W4384388111 cites W3116286104 @default.
- W4384388111 cites W3119005666 @default.
- W4384388111 cites W3137125108 @default.
- W4384388111 cites W3139883826 @default.
- W4384388111 cites W3149839747 @default.
- W4384388111 cites W3155832727 @default.
- W4384388111 cites W3158076558 @default.
- W4384388111 cites W3158150050 @default.
- W4384388111 cites W3158494520 @default.
- W4384388111 cites W3170968300 @default.
- W4384388111 cites W3174784387 @default.
- W4384388111 cites W3178941104 @default.
- W4384388111 cites W3182546273 @default.
- W4384388111 cites W3186769346 @default.
- W4384388111 cites W3189411510 @default.
- W4384388111 cites W3211661953 @default.
- W4384388111 cites W4220785415 @default.
- W4384388111 cites W4248646870 @default.
- W4384388111 cites W4255747608 @default.
- W4384388111 cites W4281758010 @default.
- W4384388111 cites W4283658720 @default.
- W4384388111 cites W4296580612 @default.
- W4384388111 cites W4307409069 @default.
- W4384388111 doi "https://doi.org/10.1038/s41598-023-38459-1" @default.
- W4384388111 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37452133" @default.
- W4384388111 hasPublicationYear "2023" @default.
- W4384388111 type Work @default.
- W4384388111 citedByCount "0" @default.
- W4384388111 crossrefType "journal-article" @default.
- W4384388111 hasAuthorship W4384388111A5020655974 @default.
- W4384388111 hasAuthorship W4384388111A5032958131 @default.
- W4384388111 hasAuthorship W4384388111A5042655412 @default.
- W4384388111 hasBestOaLocation W43843881111 @default.
- W4384388111 hasConcept C119857082 @default.
- W4384388111 hasConcept C13280743 @default.
- W4384388111 hasConcept C138885662 @default.
- W4384388111 hasConcept C153180895 @default.
- W4384388111 hasConcept C154945302 @default.
- W4384388111 hasConcept C17744445 @default.
- W4384388111 hasConcept C185798385 @default.
- W4384388111 hasConcept C199539241 @default.
- W4384388111 hasConcept C205649164 @default.
- W4384388111 hasConcept C2776359362 @default.
- W4384388111 hasConcept C2776401178 @default.
- W4384388111 hasConcept C2780233690 @default.
- W4384388111 hasConcept C38652104 @default.
- W4384388111 hasConcept C41008148 @default.
- W4384388111 hasConcept C41895202 @default.
- W4384388111 hasConcept C81363708 @default.
- W4384388111 hasConcept C94625758 @default.
- W4384388111 hasConceptScore W4384388111C119857082 @default.
- W4384388111 hasConceptScore W4384388111C13280743 @default.