Matches in SemOpenAlex for { <https://semopenalex.org/work/W2787843651> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2787843651 abstract "The artificial neural network shows powerful ability of inference, but it is still criticized for lack of interpretability and prerequisite needs of big dataset. This paper proposes the Rule-embedded Neural Network (ReNN) to overcome the shortages. ReNN first makes local-based inferences to detect local patterns, and then uses rules based on domain knowledge about the local patterns to generate rule-modulated map. After that, ReNN makes global-based inferences that synthesizes the local patterns and the rule-modulated map. To solve the optimization problem caused by rules, we use a two-stage optimization strategy to train the ReNN model. By introducing rules into ReNN, we can strengthen traditional neural networks with long-term dependencies which are difficult to learn with limited empirical dataset, thus improving inference accuracy. The complexity of neural networks can be reduced since long-term dependencies are not modeled with neural connections, and thus the amount of data needed to optimize the neural networks can be reduced. Besides, inferences from ReNN can be analyzed with both local patterns and rules, and thus have better interpretability. In this paper, ReNN has been validated with a time-series detection problem." @default.
- W2787843651 created "2018-02-23" @default.
- W2787843651 creator A5014932458 @default.
- W2787843651 date "2018-01-30" @default.
- W2787843651 modified "2023-09-25" @default.
- W2787843651 title "ReNN: Rule-embedded Neural Networks" @default.
- W2787843651 cites W1511986666 @default.
- W2787843651 cites W1582487692 @default.
- W2787843651 cites W1594355775 @default.
- W2787843651 cites W1825675169 @default.
- W2787843651 cites W1849277567 @default.
- W2787843651 cites W1903029394 @default.
- W2787843651 cites W1932198206 @default.
- W2787843651 cites W1969109407 @default.
- W2787843651 cites W1989789052 @default.
- W2787843651 cites W2006922696 @default.
- W2787843651 cites W2016979930 @default.
- W2787843651 cites W2020647649 @default.
- W2787843651 cites W2047693489 @default.
- W2787843651 cites W2056715049 @default.
- W2787843651 cites W2057674912 @default.
- W2787843651 cites W2064355504 @default.
- W2787843651 cites W2064675550 @default.
- W2787843651 cites W2095739681 @default.
- W2787843651 cites W2136429434 @default.
- W2787843651 cites W2153595771 @default.
- W2787843651 cites W2162273778 @default.
- W2787843651 cites W2163605009 @default.
- W2787843651 cites W2194775991 @default.
- W2787843651 cites W2358986845 @default.
- W2787843651 cites W2593634001 @default.
- W2787843651 cites W2610018085 @default.
- W2787843651 cites W2613328025 @default.
- W2787843651 cites W2731010577 @default.
- W2787843651 cites W2766447205 @default.
- W2787843651 cites W2781566433 @default.
- W2787843651 cites W2919115771 @default.
- W2787843651 cites W2962883557 @default.
- W2787843651 cites W2963996492 @default.
- W2787843651 cites W2964153729 @default.
- W2787843651 cites W2964308564 @default.
- W2787843651 doi "https://doi.org/10.48550/arxiv.1801.09856" @default.
- W2787843651 hasPublicationYear "2018" @default.
- W2787843651 type Work @default.
- W2787843651 sameAs 2787843651 @default.
- W2787843651 citedByCount "0" @default.
- W2787843651 crossrefType "posted-content" @default.
- W2787843651 hasAuthorship W2787843651A5014932458 @default.
- W2787843651 hasBestOaLocation W27878436511 @default.
- W2787843651 hasConcept C119857082 @default.
- W2787843651 hasConcept C138885662 @default.
- W2787843651 hasConcept C154945302 @default.
- W2787843651 hasConcept C194051981 @default.
- W2787843651 hasConcept C2776214188 @default.
- W2787843651 hasConcept C2778137410 @default.
- W2787843651 hasConcept C2781067378 @default.
- W2787843651 hasConcept C41008148 @default.
- W2787843651 hasConcept C41895202 @default.
- W2787843651 hasConcept C50644808 @default.
- W2787843651 hasConceptScore W2787843651C119857082 @default.
- W2787843651 hasConceptScore W2787843651C138885662 @default.
- W2787843651 hasConceptScore W2787843651C154945302 @default.
- W2787843651 hasConceptScore W2787843651C194051981 @default.
- W2787843651 hasConceptScore W2787843651C2776214188 @default.
- W2787843651 hasConceptScore W2787843651C2778137410 @default.
- W2787843651 hasConceptScore W2787843651C2781067378 @default.
- W2787843651 hasConceptScore W2787843651C41008148 @default.
- W2787843651 hasConceptScore W2787843651C41895202 @default.
- W2787843651 hasConceptScore W2787843651C50644808 @default.
- W2787843651 hasLocation W27878436511 @default.
- W2787843651 hasLocation W27878436512 @default.
- W2787843651 hasOpenAccess W2787843651 @default.
- W2787843651 hasPrimaryLocation W27878436511 @default.
- W2787843651 hasRelatedWork W1986582023 @default.
- W2787843651 hasRelatedWork W3006943036 @default.
- W2787843651 hasRelatedWork W4200511449 @default.
- W2787843651 hasRelatedWork W4206534706 @default.
- W2787843651 hasRelatedWork W4229079080 @default.
- W2787843651 hasRelatedWork W4299487748 @default.
- W2787843651 hasRelatedWork W4385767940 @default.
- W2787843651 hasRelatedWork W4385957992 @default.
- W2787843651 hasRelatedWork W4385965371 @default.
- W2787843651 hasRelatedWork W4386025632 @default.
- W2787843651 isParatext "false" @default.
- W2787843651 isRetracted "false" @default.
- W2787843651 magId "2787843651" @default.
- W2787843651 workType "article" @default.