Matches in SemOpenAlex for { <https://semopenalex.org/work/W3021529903> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3021529903 endingPage "174" @default.
- W3021529903 startingPage "162" @default.
- W3021529903 abstract "Several techniques were designed during last few years to improve the performance of deep architecture by means of appropriate loss functions or activation functions. Arguably, softmax is the traditionally convenient to train Deep Convolutional Neural Networks (DCNNs) for classification task. However, the modern deep learning architectures have exposed its limitation towards feature discriminability. In this paper, we offered a supervision signal for discriminative image features through a modification in softmax to boost up the power of loss function. Amending the original softmax loss and motivated by the A-softmax loss for face recognition, we fixed the angular margin to introduce a unit margin softmax loss. The improved alternative form of softmax is trainable, easy to optimize and stable for usage along with Stochastic Gradient Descent (SGD) and Laplacian Smoothing Stochastic Gradient Descent (LS-SGD) and applicable to classify the digits in image. Experimental results demonstrate a state-of-the-art performance on famous database of handwritten digits the Modified National Institute of Standards and Technology (MNIST) database." @default.
- W3021529903 created "2020-05-13" @default.
- W3021529903 creator A5028815265 @default.
- W3021529903 creator A5029784278 @default.
- W3021529903 creator A5070501516 @default.
- W3021529903 creator A5090635693 @default.
- W3021529903 date "2020-01-01" @default.
- W3021529903 modified "2023-10-14" @default.
- W3021529903 title "A Unit Softmax with Laplacian Smoothing Stochastic Gradient Descent for Deep Convolutional Neural Networks" @default.
- W3021529903 cites W114517082 @default.
- W3021529903 cites W1855169650 @default.
- W3021529903 cites W2076063813 @default.
- W3021529903 cites W2105366992 @default.
- W3021529903 cites W2134969019 @default.
- W3021529903 cites W2546302380 @default.
- W3021529903 cites W2592549397 @default.
- W3021529903 cites W2767547957 @default.
- W3021529903 cites W2794284562 @default.
- W3021529903 cites W2904609180 @default.
- W3021529903 cites W2919115771 @default.
- W3021529903 cites W2962898354 @default.
- W3021529903 cites W2963433607 @default.
- W3021529903 cites W2963466847 @default.
- W3021529903 cites W2963480765 @default.
- W3021529903 cites W2969985801 @default.
- W3021529903 cites W2994641016 @default.
- W3021529903 cites W3099206234 @default.
- W3021529903 doi "https://doi.org/10.1007/978-981-15-5232-8_14" @default.
- W3021529903 hasPublicationYear "2020" @default.
- W3021529903 type Work @default.
- W3021529903 sameAs 3021529903 @default.
- W3021529903 citedByCount "4" @default.
- W3021529903 countsByYear W30215299032019 @default.
- W3021529903 countsByYear W30215299032022 @default.
- W3021529903 countsByYear W30215299032023 @default.
- W3021529903 crossrefType "book-chapter" @default.
- W3021529903 hasAuthorship W3021529903A5028815265 @default.
- W3021529903 hasAuthorship W3021529903A5029784278 @default.
- W3021529903 hasAuthorship W3021529903A5070501516 @default.
- W3021529903 hasAuthorship W3021529903A5090635693 @default.
- W3021529903 hasConcept C108583219 @default.
- W3021529903 hasConcept C119857082 @default.
- W3021529903 hasConcept C138885662 @default.
- W3021529903 hasConcept C153180895 @default.
- W3021529903 hasConcept C153258448 @default.
- W3021529903 hasConcept C154945302 @default.
- W3021529903 hasConcept C188441871 @default.
- W3021529903 hasConcept C190502265 @default.
- W3021529903 hasConcept C206688291 @default.
- W3021529903 hasConcept C2776401178 @default.
- W3021529903 hasConcept C31972630 @default.
- W3021529903 hasConcept C3770464 @default.
- W3021529903 hasConcept C41008148 @default.
- W3021529903 hasConcept C41895202 @default.
- W3021529903 hasConcept C50644808 @default.
- W3021529903 hasConcept C774472 @default.
- W3021529903 hasConcept C81363708 @default.
- W3021529903 hasConcept C97931131 @default.
- W3021529903 hasConceptScore W3021529903C108583219 @default.
- W3021529903 hasConceptScore W3021529903C119857082 @default.
- W3021529903 hasConceptScore W3021529903C138885662 @default.
- W3021529903 hasConceptScore W3021529903C153180895 @default.
- W3021529903 hasConceptScore W3021529903C153258448 @default.
- W3021529903 hasConceptScore W3021529903C154945302 @default.
- W3021529903 hasConceptScore W3021529903C188441871 @default.
- W3021529903 hasConceptScore W3021529903C190502265 @default.
- W3021529903 hasConceptScore W3021529903C206688291 @default.
- W3021529903 hasConceptScore W3021529903C2776401178 @default.
- W3021529903 hasConceptScore W3021529903C31972630 @default.
- W3021529903 hasConceptScore W3021529903C3770464 @default.
- W3021529903 hasConceptScore W3021529903C41008148 @default.
- W3021529903 hasConceptScore W3021529903C41895202 @default.
- W3021529903 hasConceptScore W3021529903C50644808 @default.
- W3021529903 hasConceptScore W3021529903C774472 @default.
- W3021529903 hasConceptScore W3021529903C81363708 @default.
- W3021529903 hasConceptScore W3021529903C97931131 @default.
- W3021529903 hasLocation W30215299031 @default.
- W3021529903 hasOpenAccess W3021529903 @default.
- W3021529903 hasPrimaryLocation W30215299031 @default.
- W3021529903 hasRelatedWork W2044529480 @default.
- W3021529903 hasRelatedWork W2743258233 @default.
- W3021529903 hasRelatedWork W2758063741 @default.
- W3021529903 hasRelatedWork W2771907641 @default.
- W3021529903 hasRelatedWork W2883041339 @default.
- W3021529903 hasRelatedWork W2977314777 @default.
- W3021529903 hasRelatedWork W2990633046 @default.
- W3021529903 hasRelatedWork W2998469040 @default.
- W3021529903 hasRelatedWork W3156786002 @default.
- W3021529903 hasRelatedWork W4309224979 @default.
- W3021529903 isParatext "false" @default.
- W3021529903 isRetracted "false" @default.
- W3021529903 magId "3021529903" @default.
- W3021529903 workType "book-chapter" @default.