Matches in SemOpenAlex for { <https://semopenalex.org/work/W2938863785> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2938863785 abstract "The emergence of deep learning networks raises a need for explainable AI so that users and domain experts can be confident applying them to high-risk decisions. In this paper, we leverage data from the latent space induced by deep learning models to learn stereotypical representations or during training to elucidate the algorithmic decision-making process. We study how leveraging prototypes effect classification decisions of two dimensional time-series data in a few different settings: (1) electrocardiogram (ECG) waveforms to detect clinical bradycardia, a slowing of heart rate, in preterm infants, (2) respiration waveforms to detect apnea of prematurity, and (3) audio waveforms to classify spoken digits. We improve upon existing models by optimizing for increased prototype diversity and robustness, visualize how these prototypes in the latent space are used by the model to distinguish classes, and show that prototypes are capable of learning features on two dimensional time-series data to produce explainable insights during classification tasks. We show that the prototypes are capable of learning real-world features - bradycardia in ECG, apnea in respiration, and articulation in speech - as well as features within sub-classes. Our novel work leverages learned prototypical framework on two dimensional time-series data to produce explainable insights during classification tasks." @default.
- W2938863785 created "2019-04-25" @default.
- W2938863785 creator A5041507960 @default.
- W2938863785 creator A5045494697 @default.
- W2938863785 creator A5058100924 @default.
- W2938863785 creator A5061696723 @default.
- W2938863785 date "2019-04-18" @default.
- W2938863785 modified "2023-10-16" @default.
- W2938863785 title "Explaining Deep Classification of Time-Series Data with Learned Prototypes" @default.
- W2938863785 cites W1509441537 @default.
- W2938863785 cites W1535611613 @default.
- W2938863785 cites W1569158208 @default.
- W2938863785 cites W1975906543 @default.
- W2938863785 cites W1996796871 @default.
- W2938863785 cites W2094691727 @default.
- W2938863785 cites W2150900351 @default.
- W2938863785 cites W2162800060 @default.
- W2938863785 cites W2187089797 @default.
- W2938863785 cites W2225959205 @default.
- W2938863785 cites W2282821441 @default.
- W2938863785 cites W2295107390 @default.
- W2938863785 cites W2557126235 @default.
- W2938863785 cites W2767858146 @default.
- W2938863785 cites W2797694788 @default.
- W2938863785 cites W2811104224 @default.
- W2938863785 cites W2889838428 @default.
- W2938863785 cites W2897955056 @default.
- W2938863785 cites W2901939789 @default.
- W2938863785 cites W2912802472 @default.
- W2938863785 cites W2936774411 @default.
- W2938863785 cites W2940573101 @default.
- W2938863785 cites W2949382160 @default.
- W2938863785 cites W2964180856 @default.
- W2938863785 cites W2971048680 @default.
- W2938863785 cites W2974440810 @default.
- W2938863785 hasPublicationYear "2019" @default.
- W2938863785 type Work @default.
- W2938863785 sameAs 2938863785 @default.
- W2938863785 citedByCount "12" @default.
- W2938863785 countsByYear W29388637852019 @default.
- W2938863785 countsByYear W29388637852020 @default.
- W2938863785 countsByYear W29388637852021 @default.
- W2938863785 crossrefType "posted-content" @default.
- W2938863785 hasAuthorship W2938863785A5041507960 @default.
- W2938863785 hasAuthorship W2938863785A5045494697 @default.
- W2938863785 hasAuthorship W2938863785A5058100924 @default.
- W2938863785 hasAuthorship W2938863785A5061696723 @default.
- W2938863785 hasConcept C104317684 @default.
- W2938863785 hasConcept C108583219 @default.
- W2938863785 hasConcept C119857082 @default.
- W2938863785 hasConcept C151406439 @default.
- W2938863785 hasConcept C153083717 @default.
- W2938863785 hasConcept C154945302 @default.
- W2938863785 hasConcept C185592680 @default.
- W2938863785 hasConcept C28490314 @default.
- W2938863785 hasConcept C41008148 @default.
- W2938863785 hasConcept C55493867 @default.
- W2938863785 hasConcept C63479239 @default.
- W2938863785 hasConceptScore W2938863785C104317684 @default.
- W2938863785 hasConceptScore W2938863785C108583219 @default.
- W2938863785 hasConceptScore W2938863785C119857082 @default.
- W2938863785 hasConceptScore W2938863785C151406439 @default.
- W2938863785 hasConceptScore W2938863785C153083717 @default.
- W2938863785 hasConceptScore W2938863785C154945302 @default.
- W2938863785 hasConceptScore W2938863785C185592680 @default.
- W2938863785 hasConceptScore W2938863785C28490314 @default.
- W2938863785 hasConceptScore W2938863785C41008148 @default.
- W2938863785 hasConceptScore W2938863785C55493867 @default.
- W2938863785 hasConceptScore W2938863785C63479239 @default.
- W2938863785 hasOpenAccess W2938863785 @default.
- W2938863785 hasRelatedWork W2030863907 @default.
- W2938863785 hasRelatedWork W2107789863 @default.
- W2938863785 hasRelatedWork W2184188583 @default.
- W2938863785 hasRelatedWork W2282821441 @default.
- W2938863785 hasRelatedWork W2783639327 @default.
- W2938863785 hasRelatedWork W2962862931 @default.
- W2938863785 hasRelatedWork W2964716450 @default.
- W2938863785 hasRelatedWork W2971156299 @default.
- W2938863785 hasRelatedWork W3009344359 @default.
- W2938863785 hasRelatedWork W3011806746 @default.
- W2938863785 hasRelatedWork W3034131409 @default.
- W2938863785 hasRelatedWork W3080092352 @default.
- W2938863785 hasRelatedWork W3097652626 @default.
- W2938863785 hasRelatedWork W3101349400 @default.
- W2938863785 hasRelatedWork W3128362522 @default.
- W2938863785 hasRelatedWork W3129999520 @default.
- W2938863785 hasRelatedWork W3132560851 @default.
- W2938863785 hasRelatedWork W3146622378 @default.
- W2938863785 hasRelatedWork W3148150216 @default.
- W2938863785 hasRelatedWork W3160631096 @default.
- W2938863785 isParatext "false" @default.
- W2938863785 isRetracted "false" @default.
- W2938863785 magId "2938863785" @default.
- W2938863785 workType "article" @default.