Matches in SemOpenAlex for { <https://semopenalex.org/work/W2782699075> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2782699075 abstract "We introduce the concept of diverse activation functions, and apply them into Convolutional Auto-Encoder (CAE) to develop diverse activation CAE (DaCAE), which considerably reduces the reconstruction loss. In contrast to vanilla CAE only with activation functions of the same types, DaCAE incorporates diverse activations by considering their cooperation and location. In terms of the reconstruction capability, DaCAE significantly outperforms vanilla CAE and full connected Auto-Encoder, and we conclude rules of thumb on designing diverse activations networks. Based on the high quality of the latent bottleneck features extracted from DaCAE, we demonstrate a satisfying advantage that fuzzy rules classifier performs better than softmax layer in supervised learning. These results could be seen as new research points in the attempts at using diverse activations to train deep neural networks and combining fuzzy inference systems with deep learning." @default.
- W2782699075 created "2018-01-26" @default.
- W2782699075 creator A5015829772 @default.
- W2782699075 creator A5038219098 @default.
- W2782699075 creator A5048793108 @default.
- W2782699075 creator A5060295796 @default.
- W2782699075 creator A5070559820 @default.
- W2782699075 creator A5071469942 @default.
- W2782699075 date "2017-11-01" @default.
- W2782699075 modified "2023-10-18" @default.
- W2782699075 title "Diverse activation functions in deep learning" @default.
- W2782699075 cites W1677182931 @default.
- W2782699075 cites W1694178301 @default.
- W2782699075 cites W1806891645 @default.
- W2782699075 cites W1849277567 @default.
- W2782699075 cites W1921523184 @default.
- W2782699075 cites W2136655611 @default.
- W2782699075 cites W2156387975 @default.
- W2782699075 cites W2163605009 @default.
- W2782699075 cites W2176412452 @default.
- W2782699075 cites W2193413348 @default.
- W2782699075 cites W2194435393 @default.
- W2782699075 cites W2293078015 @default.
- W2782699075 cites W2436203038 @default.
- W2782699075 cites W2528639018 @default.
- W2782699075 cites W2963703360 @default.
- W2782699075 cites W630242894 @default.
- W2782699075 doi "https://doi.org/10.1109/iske.2017.8258768" @default.
- W2782699075 hasPublicationYear "2017" @default.
- W2782699075 type Work @default.
- W2782699075 sameAs 2782699075 @default.
- W2782699075 citedByCount "4" @default.
- W2782699075 countsByYear W27826990752019 @default.
- W2782699075 countsByYear W27826990752020 @default.
- W2782699075 countsByYear W27826990752022 @default.
- W2782699075 crossrefType "proceedings-article" @default.
- W2782699075 hasAuthorship W2782699075A5015829772 @default.
- W2782699075 hasAuthorship W2782699075A5038219098 @default.
- W2782699075 hasAuthorship W2782699075A5048793108 @default.
- W2782699075 hasAuthorship W2782699075A5060295796 @default.
- W2782699075 hasAuthorship W2782699075A5070559820 @default.
- W2782699075 hasAuthorship W2782699075A5071469942 @default.
- W2782699075 hasConcept C108583219 @default.
- W2782699075 hasConcept C119857082 @default.
- W2782699075 hasConcept C154945302 @default.
- W2782699075 hasConcept C188441871 @default.
- W2782699075 hasConcept C190502265 @default.
- W2782699075 hasConcept C2776214188 @default.
- W2782699075 hasConcept C41008148 @default.
- W2782699075 hasConcept C81363708 @default.
- W2782699075 hasConcept C95623464 @default.
- W2782699075 hasConceptScore W2782699075C108583219 @default.
- W2782699075 hasConceptScore W2782699075C119857082 @default.
- W2782699075 hasConceptScore W2782699075C154945302 @default.
- W2782699075 hasConceptScore W2782699075C188441871 @default.
- W2782699075 hasConceptScore W2782699075C190502265 @default.
- W2782699075 hasConceptScore W2782699075C2776214188 @default.
- W2782699075 hasConceptScore W2782699075C41008148 @default.
- W2782699075 hasConceptScore W2782699075C81363708 @default.
- W2782699075 hasConceptScore W2782699075C95623464 @default.
- W2782699075 hasLocation W27826990751 @default.
- W2782699075 hasOpenAccess W2782699075 @default.
- W2782699075 hasPrimaryLocation W27826990751 @default.
- W2782699075 hasRelatedWork W1423376249 @default.
- W2782699075 hasRelatedWork W2079073952 @default.
- W2782699075 hasRelatedWork W2267244539 @default.
- W2782699075 hasRelatedWork W2279398222 @default.
- W2782699075 hasRelatedWork W2397746618 @default.
- W2782699075 hasRelatedWork W2467256294 @default.
- W2782699075 hasRelatedWork W2551045169 @default.
- W2782699075 hasRelatedWork W2745213438 @default.
- W2782699075 hasRelatedWork W2762208110 @default.
- W2782699075 hasRelatedWork W2902690839 @default.
- W2782699075 hasRelatedWork W2904410459 @default.
- W2782699075 hasRelatedWork W2935136802 @default.
- W2782699075 hasRelatedWork W2941045407 @default.
- W2782699075 hasRelatedWork W2944810377 @default.
- W2782699075 hasRelatedWork W2963294943 @default.
- W2782699075 hasRelatedWork W2997748707 @default.
- W2782699075 hasRelatedWork W3010968125 @default.
- W2782699075 hasRelatedWork W3048478353 @default.
- W2782699075 hasRelatedWork W3105627983 @default.
- W2782699075 hasRelatedWork W3201909459 @default.
- W2782699075 isParatext "false" @default.
- W2782699075 isRetracted "false" @default.
- W2782699075 magId "2782699075" @default.
- W2782699075 workType "article" @default.