FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950065461> ?p ?o ?g. }

• W2950065461 abstract "The promise of ANNs to automatically discover and extract useful features/patterns from data without dwelling on domain expertise although seems highly promising but comes at the cost of high reliance on large amount of accurately labeled data, which is often hard to acquire and formulate especially in time-series domains like anomaly detection, natural disaster management, predictive maintenance and healthcare. As these networks completely rely on data and ignore a very important modality i.e. expert, they are unable to harvest any benefit from the expert knowledge, which in many cases is very useful. In this paper, we try to bridge the gap between these data driven and expert knowledge based systems by introducing a novel framework for incorporating expert knowledge into the network (KINN). Integrating expert knowledge into the network has three key advantages: (a) Reduction in the amount of data needed to train the model, (b) provision of a lower bound on the performance of the resulting classifier by obtaining the best of both worlds, and (c) improved convergence of model parameters (model converges in smaller number of epochs). Although experts are extremely good in solving different tasks, there are some trends and patterns, which are usually hidden only in the data. Therefore, KINN employs a novel residual knowledge incorporation scheme, which can automatically determine the quality of the predictions made by the expert and rectify it accordingly by learning the trends/patterns from data. Specifically, the method tries to use information contained in one modality to complement information missed by the other. We evaluated KINN on a real world traffic flow prediction problem. KINN significantly superseded performance of both the expert and as well as the base network (LSTM in this case) when evaluated in isolation, highlighting its superiority for the task." @default.
• W2950065461 created "2019-06-27" @default.
• W2950065461 creator A5001025348 @default.
• W2950065461 creator A5011903664 @default.
• W2950065461 creator A5053635416 @default.
• W2950065461 creator A5058813180 @default.
• W2950065461 creator A5071991246 @default.
• W2950065461 creator A5073903451 @default.
• W2950065461 date "2019-02-15" @default.
• W2950065461 modified "2023-09-22" @default.
• W2950065461 title "KINN: Incorporating Expert Knowledge in Neural Networks" @default.
• W2950065461 cites W1944454310 @default.
• W2950065461 cites W2156387975 @default.
• W2950065461 cites W2160815625 @default.
• W2950065461 cites W2168332560 @default.
• W2950065461 cites W2194775991 @default.
• W2950065461 cites W2404399993 @default.
• W2950065461 cites W2573379274 @default.
• W2950065461 cites W2604912255 @default.
• W2950065461 cites W2915347557 @default.
• W2950065461 cites W2962824709 @default.
• W2950065461 cites W2962843773 @default.
• W2950065461 cites W2963737801 @default.
• W2950065461 cites W2963918774 @default.
• W2950065461 cites W2964153729 @default.
• W2950065461 cites W2114001875 @default.
• W2950065461 hasPublicationYear "2019" @default.
• W2950065461 type Work @default.
• W2950065461 sameAs 2950065461 @default.
• W2950065461 citedByCount "0" @default.
• W2950065461 crossrefType "posted-content" @default.
• W2950065461 hasAuthorship W2950065461A5001025348 @default.
• W2950065461 hasAuthorship W2950065461A5011903664 @default.
• W2950065461 hasAuthorship W2950065461A5053635416 @default.
• W2950065461 hasAuthorship W2950065461A5058813180 @default.
• W2950065461 hasAuthorship W2950065461A5071991246 @default.
• W2950065461 hasAuthorship W2950065461A5073903451 @default.
• W2950065461 hasConcept C100776233 @default.
• W2950065461 hasConcept C11413529 @default.
• W2950065461 hasConcept C119857082 @default.
• W2950065461 hasConcept C124101348 @default.
• W2950065461 hasConcept C126322002 @default.
• W2950065461 hasConcept C154945302 @default.
• W2950065461 hasConcept C155512373 @default.
• W2950065461 hasConcept C207685749 @default.
• W2950065461 hasConcept C26517878 @default.
• W2950065461 hasConcept C38652104 @default.
• W2950065461 hasConcept C41008148 @default.
• W2950065461 hasConcept C50644808 @default.
• W2950065461 hasConcept C58328972 @default.
• W2950065461 hasConcept C71924100 @default.
• W2950065461 hasConcept C95623464 @default.
• W2950065461 hasConceptScore W2950065461C100776233 @default.
• W2950065461 hasConceptScore W2950065461C11413529 @default.
• W2950065461 hasConceptScore W2950065461C119857082 @default.
• W2950065461 hasConceptScore W2950065461C124101348 @default.
• W2950065461 hasConceptScore W2950065461C126322002 @default.
• W2950065461 hasConceptScore W2950065461C154945302 @default.
• W2950065461 hasConceptScore W2950065461C155512373 @default.
• W2950065461 hasConceptScore W2950065461C207685749 @default.
• W2950065461 hasConceptScore W2950065461C26517878 @default.
• W2950065461 hasConceptScore W2950065461C38652104 @default.
• W2950065461 hasConceptScore W2950065461C41008148 @default.
• W2950065461 hasConceptScore W2950065461C50644808 @default.
• W2950065461 hasConceptScore W2950065461C58328972 @default.
• W2950065461 hasConceptScore W2950065461C71924100 @default.
• W2950065461 hasConceptScore W2950065461C95623464 @default.
• W2950065461 hasLocation W29500654611 @default.
• W2950065461 hasOpenAccess W2950065461 @default.
• W2950065461 hasPrimaryLocation W29500654611 @default.
• W2950065461 hasRelatedWork W147807230 @default.
• W2950065461 hasRelatedWork W1572890417 @default.
• W2950065461 hasRelatedWork W1982643701 @default.
• W2950065461 hasRelatedWork W2123792384 @default.
• W2950065461 hasRelatedWork W2130420534 @default.
• W2950065461 hasRelatedWork W2252012216 @default.
• W2950065461 hasRelatedWork W2625431422 @default.
• W2950065461 hasRelatedWork W2783201451 @default.
• W2950065461 hasRelatedWork W2845698941 @default.
• W2950065461 hasRelatedWork W2902659398 @default.
• W2950065461 hasRelatedWork W2913385702 @default.
• W2950065461 hasRelatedWork W2970657225 @default.
• W2950065461 hasRelatedWork W2971403594 @default.
• W2950065461 hasRelatedWork W2976879737 @default.
• W2950065461 hasRelatedWork W3088496551 @default.
• W2950065461 hasRelatedWork W3125809029 @default.
• W2950065461 hasRelatedWork W3126320871 @default.
• W2950065461 hasRelatedWork W3128747898 @default.
• W2950065461 hasRelatedWork W3170170419 @default.
• W2950065461 hasRelatedWork W3205180534 @default.
• W2950065461 isParatext "false" @default.
• W2950065461 isRetracted "false" @default.
• W2950065461 magId "2950065461" @default.
• W2950065461 workType "article" @default.