Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199774549> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3199774549 abstract "We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process. This way we can a) find the most influential training examples during training and b) analyze which classes attributed most to the final representation. Our method is general: it can be wrapped around any iterative optimization procedure and covers a variety of neural network architectures, including feed-forward networks and convolutional neural networks. We first propose a method for stochastic training with single training instances, but continue to also derive a variant for the common mini-batch training. In experimental evaluations, we show that our method identifies highly representative training instances that can be used as an explanation. Additionally, we propose a visualization that provides explanations in the form of aggregated statistics over the whole training process." @default.
- W3199774549 created "2021-09-27" @default.
- W3199774549 creator A5005777739 @default.
- W3199774549 creator A5065328227 @default.
- W3199774549 date "2021-09-13" @default.
- W3199774549 modified "2023-09-26" @default.
- W3199774549 title "Explaining Deep Learning Representations by Tracing the Training Process." @default.
- W3199774549 cites W104184427 @default.
- W3199774549 cites W1537462412 @default.
- W3199774549 cites W2788007910 @default.
- W3199774549 cites W2803354268 @default.
- W3199774549 cites W2891612330 @default.
- W3199774549 cites W2900569176 @default.
- W3199774549 cites W2949117887 @default.
- W3199774549 cites W2949605285 @default.
- W3199774549 cites W2950411297 @default.
- W3199774549 cites W2962711740 @default.
- W3199774549 cites W2962851944 @default.
- W3199774549 cites W3042984546 @default.
- W3199774549 cites W3088647504 @default.
- W3199774549 cites W3133543405 @default.
- W3199774549 cites W3164909318 @default.
- W3199774549 cites W3021975806 @default.
- W3199774549 hasPublicationYear "2021" @default.
- W3199774549 type Work @default.
- W3199774549 sameAs 3199774549 @default.
- W3199774549 citedByCount "0" @default.
- W3199774549 crossrefType "posted-content" @default.
- W3199774549 hasAuthorship W3199774549A5005777739 @default.
- W3199774549 hasAuthorship W3199774549A5065328227 @default.
- W3199774549 hasConcept C108583219 @default.
- W3199774549 hasConcept C111919701 @default.
- W3199774549 hasConcept C119857082 @default.
- W3199774549 hasConcept C121332964 @default.
- W3199774549 hasConcept C136197465 @default.
- W3199774549 hasConcept C138673069 @default.
- W3199774549 hasConcept C153294291 @default.
- W3199774549 hasConcept C154945302 @default.
- W3199774549 hasConcept C17744445 @default.
- W3199774549 hasConcept C199539241 @default.
- W3199774549 hasConcept C2776359362 @default.
- W3199774549 hasConcept C2777211547 @default.
- W3199774549 hasConcept C2984842247 @default.
- W3199774549 hasConcept C36464697 @default.
- W3199774549 hasConcept C41008148 @default.
- W3199774549 hasConcept C50644808 @default.
- W3199774549 hasConcept C81363708 @default.
- W3199774549 hasConcept C94625758 @default.
- W3199774549 hasConcept C98045186 @default.
- W3199774549 hasConceptScore W3199774549C108583219 @default.
- W3199774549 hasConceptScore W3199774549C111919701 @default.
- W3199774549 hasConceptScore W3199774549C119857082 @default.
- W3199774549 hasConceptScore W3199774549C121332964 @default.
- W3199774549 hasConceptScore W3199774549C136197465 @default.
- W3199774549 hasConceptScore W3199774549C138673069 @default.
- W3199774549 hasConceptScore W3199774549C153294291 @default.
- W3199774549 hasConceptScore W3199774549C154945302 @default.
- W3199774549 hasConceptScore W3199774549C17744445 @default.
- W3199774549 hasConceptScore W3199774549C199539241 @default.
- W3199774549 hasConceptScore W3199774549C2776359362 @default.
- W3199774549 hasConceptScore W3199774549C2777211547 @default.
- W3199774549 hasConceptScore W3199774549C2984842247 @default.
- W3199774549 hasConceptScore W3199774549C36464697 @default.
- W3199774549 hasConceptScore W3199774549C41008148 @default.
- W3199774549 hasConceptScore W3199774549C50644808 @default.
- W3199774549 hasConceptScore W3199774549C81363708 @default.
- W3199774549 hasConceptScore W3199774549C94625758 @default.
- W3199774549 hasConceptScore W3199774549C98045186 @default.
- W3199774549 hasLocation W31997745491 @default.
- W3199774549 hasOpenAccess W3199774549 @default.
- W3199774549 hasPrimaryLocation W31997745491 @default.
- W3199774549 hasRelatedWork W2140833774 @default.
- W3199774549 hasRelatedWork W2254691124 @default.
- W3199774549 hasRelatedWork W2562979205 @default.
- W3199774549 hasRelatedWork W2574741565 @default.
- W3199774549 hasRelatedWork W2750881831 @default.
- W3199774549 hasRelatedWork W2770650464 @default.
- W3199774549 hasRelatedWork W2782784481 @default.
- W3199774549 hasRelatedWork W2787607521 @default.
- W3199774549 hasRelatedWork W2949847915 @default.
- W3199774549 hasRelatedWork W2950421700 @default.
- W3199774549 hasRelatedWork W2962812272 @default.
- W3199774549 hasRelatedWork W3015739188 @default.
- W3199774549 hasRelatedWork W3092916550 @default.
- W3199774549 hasRelatedWork W3120931074 @default.
- W3199774549 hasRelatedWork W3165418502 @default.
- W3199774549 hasRelatedWork W3174659074 @default.
- W3199774549 hasRelatedWork W3176637778 @default.
- W3199774549 hasRelatedWork W3200653887 @default.
- W3199774549 hasRelatedWork W3201342094 @default.
- W3199774549 hasRelatedWork W98970954 @default.
- W3199774549 isParatext "false" @default.
- W3199774549 isRetracted "false" @default.
- W3199774549 magId "3199774549" @default.
- W3199774549 workType "article" @default.