FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947380094> ?p ?o ?g. }

• W2947380094 abstract "This paper proposes a deep convolutional neural network model for ordinal regression by considering a family of probabilistic ordinal link functions in the output layer. The link functions are those used for cumulative link models, which are traditional statistical linear models based on projecting each pattern into a 1-dimensional space. A set of ordered thresholds splits this space into the different classes of the problem. In our case, the projections are estimated by a non-linear deep neural network. To further improve the results, we combine these ordinal models with a loss function that takes into account the distance between the categories, based on the weighted Kappa index. Three different link functions are studied in the experimental study, and the results are contrasted with statistical analysis. The experiments run over two different ordinal classification problems, and the statistical tests confirm that these models improve the results of a nominal model and outperform other proposals considered in the literature." @default.
• W2947380094 created "2019-06-07" @default.
• W2947380094 creator A5009080021 @default.
• W2947380094 creator A5063964437 @default.
• W2947380094 creator A5086980043 @default.
• W2947380094 date "2019-05-27" @default.
• W2947380094 modified "2023-10-18" @default.
• W2947380094 title "Deep ordinal classification based on cumulative link models." @default.
• W2947380094 cites W1901129140 @default.
• W2947380094 cites W1903029394 @default.
• W2947380094 cites W1925417509 @default.
• W2947380094 cites W1950117310 @default.
• W2947380094 cites W1965804146 @default.
• W2947380094 cites W1976948919 @default.
• W2947380094 cites W2000200144 @default.
• W2947380094 cites W2025183033 @default.
• W2947380094 cites W2101635534 @default.
• W2947380094 cites W2102605133 @default.
• W2947380094 cites W2107878631 @default.
• W2947380094 cites W2145339207 @default.
• W2947380094 cites W2160815625 @default.
• W2947380094 cites W2176412452 @default.
• W2947380094 cites W2190044943 @default.
• W2947380094 cites W2194775991 @default.
• W2947380094 cites W2210976041 @default.
• W2947380094 cites W2293706247 @default.
• W2947380094 cites W2318032547 @default.
• W2947380094 cites W2318802957 @default.
• W2947380094 cites W2440214111 @default.
• W2947380094 cites W2559975580 @default.
• W2947380094 cites W2560046091 @default.
• W2947380094 cites W2566000288 @default.
• W2947380094 cites W2585123518 @default.
• W2947380094 cites W2590001609 @default.
• W2947380094 cites W2601707599 @default.
• W2947380094 cites W2612395532 @default.
• W2947380094 cites W2742048379 @default.
• W2947380094 cites W2747506362 @default.
• W2947380094 cites W2753757913 @default.
• W2947380094 cites W2769908547 @default.
• W2947380094 cites W2790840457 @default.
• W2947380094 cites W2798655965 @default.
• W2947380094 cites W2801122074 @default.
• W2947380094 cites W2894781902 @default.
• W2947380094 cites W2894879246 @default.
• W2947380094 cites W2895960267 @default.
• W2947380094 cites W2919115771 @default.
• W2947380094 cites W2949117887 @default.
• W2947380094 cites W2963178695 @default.
• W2947380094 cites W2963237621 @default.
• W2947380094 cites W2963488291 @default.
• W2947380094 cites W2964054038 @default.
• W2947380094 cites W2964121744 @default.
• W2947380094 cites W2988119488 @default.
• W2947380094 cites W54257720 @default.
• W2947380094 hasPublicationYear "2019" @default.
• W2947380094 type Work @default.
• W2947380094 sameAs 2947380094 @default.
• W2947380094 citedByCount "1" @default.
• W2947380094 countsByYear W29473800942019 @default.
• W2947380094 crossrefType "posted-content" @default.
• W2947380094 hasAuthorship W2947380094A5009080021 @default.
• W2947380094 hasAuthorship W2947380094A5063964437 @default.
• W2947380094 hasAuthorship W2947380094A5086980043 @default.
• W2947380094 hasConcept C105795698 @default.
• W2947380094 hasConcept C110313322 @default.
• W2947380094 hasConcept C114289077 @default.
• W2947380094 hasConcept C114614502 @default.
• W2947380094 hasConcept C14036430 @default.
• W2947380094 hasConcept C154945302 @default.
• W2947380094 hasConcept C163175372 @default.
• W2947380094 hasConcept C177264268 @default.
• W2947380094 hasConcept C199360897 @default.
• W2947380094 hasConcept C2778753846 @default.
• W2947380094 hasConcept C33923547 @default.
• W2947380094 hasConcept C41008148 @default.
• W2947380094 hasConcept C49937458 @default.
• W2947380094 hasConcept C50644808 @default.
• W2947380094 hasConcept C78458016 @default.
• W2947380094 hasConcept C81363708 @default.
• W2947380094 hasConcept C85461838 @default.
• W2947380094 hasConcept C86803240 @default.
• W2947380094 hasConceptScore W2947380094C105795698 @default.
• W2947380094 hasConceptScore W2947380094C110313322 @default.
• W2947380094 hasConceptScore W2947380094C114289077 @default.
• W2947380094 hasConceptScore W2947380094C114614502 @default.
• W2947380094 hasConceptScore W2947380094C14036430 @default.
• W2947380094 hasConceptScore W2947380094C154945302 @default.
• W2947380094 hasConceptScore W2947380094C163175372 @default.
• W2947380094 hasConceptScore W2947380094C177264268 @default.
• W2947380094 hasConceptScore W2947380094C199360897 @default.
• W2947380094 hasConceptScore W2947380094C2778753846 @default.
• W2947380094 hasConceptScore W2947380094C33923547 @default.
• W2947380094 hasConceptScore W2947380094C41008148 @default.
• W2947380094 hasConceptScore W2947380094C49937458 @default.
• W2947380094 hasConceptScore W2947380094C50644808 @default.
• W2947380094 hasConceptScore W2947380094C78458016 @default.
• W2947380094 hasConceptScore W2947380094C81363708 @default.
• W2947380094 hasConceptScore W2947380094C85461838 @default.
• W2947380094 hasConceptScore W2947380094C86803240 @default.

• next