Matches in SemOpenAlex for { <https://semopenalex.org/work/W2990562294> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2990562294 endingPage "140" @default.
- W2990562294 startingPage "125" @default.
- W2990562294 abstract "Multi-label classification (MLC) is an important class of machine learning problems that come with a wide spectrum of applications, each demanding a possibly different evaluation criterion. When solving the MLC problems, we generally expect the learning algorithm to take the hidden correlation of the labels into account to improve the prediction performance. Extracting the hidden correlation is generally a challenging task. In this work, we propose a novel deep learning framework to better extract the hidden correlation with the help of the memory structure within recurrent neural networks. The memory stores the temporary guesses on the labels and effectively allows the framework to rethink about the goodness and correlation of the guesses before making the final prediction. Furthermore, the rethinking process makes it easy to adapt to different evaluation criteria to match real-world application needs. In particular, the framework can be trained in an end-to-end style with respect to any given MLC evaluation criteria. The end-to-end design can be seamlessly combined with other deep learning techniques to conquer challenging MLC problems like image tagging. Experimental results across many real-world data sets justify that the rethinking framework indeed improves MLC performance across different evaluation criteria and leads to superior performance over state-of-the-art MLC algorithms." @default.
- W2990562294 created "2019-12-05" @default.
- W2990562294 creator A5008335614 @default.
- W2990562294 creator A5033186377 @default.
- W2990562294 creator A5048005939 @default.
- W2990562294 creator A5079838492 @default.
- W2990562294 date "2018-02-01" @default.
- W2990562294 modified "2023-09-27" @default.
- W2990562294 title "Deep Learning with a Rethinking Structure for Multi-label Classification" @default.
- W2990562294 hasPublicationYear "2018" @default.
- W2990562294 type Work @default.
- W2990562294 sameAs 2990562294 @default.
- W2990562294 citedByCount "1" @default.
- W2990562294 countsByYear W29905622942021 @default.
- W2990562294 crossrefType "proceedings-article" @default.
- W2990562294 hasAuthorship W2990562294A5008335614 @default.
- W2990562294 hasAuthorship W2990562294A5033186377 @default.
- W2990562294 hasAuthorship W2990562294A5048005939 @default.
- W2990562294 hasAuthorship W2990562294A5079838492 @default.
- W2990562294 hasConcept C108583219 @default.
- W2990562294 hasConcept C111919701 @default.
- W2990562294 hasConcept C11413529 @default.
- W2990562294 hasConcept C117220453 @default.
- W2990562294 hasConcept C119857082 @default.
- W2990562294 hasConcept C154945302 @default.
- W2990562294 hasConcept C162324750 @default.
- W2990562294 hasConcept C187736073 @default.
- W2990562294 hasConcept C2524010 @default.
- W2990562294 hasConcept C2777212361 @default.
- W2990562294 hasConcept C2780451532 @default.
- W2990562294 hasConcept C33923547 @default.
- W2990562294 hasConcept C41008148 @default.
- W2990562294 hasConcept C50644808 @default.
- W2990562294 hasConcept C71559656 @default.
- W2990562294 hasConcept C98045186 @default.
- W2990562294 hasConceptScore W2990562294C108583219 @default.
- W2990562294 hasConceptScore W2990562294C111919701 @default.
- W2990562294 hasConceptScore W2990562294C11413529 @default.
- W2990562294 hasConceptScore W2990562294C117220453 @default.
- W2990562294 hasConceptScore W2990562294C119857082 @default.
- W2990562294 hasConceptScore W2990562294C154945302 @default.
- W2990562294 hasConceptScore W2990562294C162324750 @default.
- W2990562294 hasConceptScore W2990562294C187736073 @default.
- W2990562294 hasConceptScore W2990562294C2524010 @default.
- W2990562294 hasConceptScore W2990562294C2777212361 @default.
- W2990562294 hasConceptScore W2990562294C2780451532 @default.
- W2990562294 hasConceptScore W2990562294C33923547 @default.
- W2990562294 hasConceptScore W2990562294C41008148 @default.
- W2990562294 hasConceptScore W2990562294C50644808 @default.
- W2990562294 hasConceptScore W2990562294C71559656 @default.
- W2990562294 hasConceptScore W2990562294C98045186 @default.
- W2990562294 hasLocation W29905622941 @default.
- W2990562294 hasOpenAccess W2990562294 @default.
- W2990562294 hasPrimaryLocation W29905622941 @default.
- W2990562294 hasRelatedWork W1492130155 @default.
- W2990562294 hasRelatedWork W1499276978 @default.
- W2990562294 hasRelatedWork W1998752042 @default.
- W2990562294 hasRelatedWork W2086810836 @default.
- W2990562294 hasRelatedWork W2107213321 @default.
- W2990562294 hasRelatedWork W2195855237 @default.
- W2990562294 hasRelatedWork W2583789430 @default.
- W2990562294 hasRelatedWork W2787518933 @default.
- W2990562294 hasRelatedWork W2803348503 @default.
- W2990562294 hasRelatedWork W2808649045 @default.
- W2990562294 hasRelatedWork W2810053714 @default.
- W2990562294 hasRelatedWork W2913698966 @default.
- W2990562294 hasRelatedWork W2951324921 @default.
- W2990562294 hasRelatedWork W2972715831 @default.
- W2990562294 hasRelatedWork W2981850339 @default.
- W2990562294 hasRelatedWork W2998390358 @default.
- W2990562294 hasRelatedWork W3013319798 @default.
- W2990562294 hasRelatedWork W3105771849 @default.
- W2990562294 hasRelatedWork W3206022707 @default.
- W2990562294 hasRelatedWork W1902813296 @default.
- W2990562294 isParatext "false" @default.
- W2990562294 isRetracted "false" @default.
- W2990562294 magId "2990562294" @default.
- W2990562294 workType "article" @default.