FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137266700> ?p ?o ?g. }

• W3137266700 endingPage "358" @default.
• W3137266700 startingPage "333" @default.
• W3137266700 abstract "Researchers often treat data-driven and theory-driven models as two disparate or even conflicting methods in travel behavior analysis. However, the two methods are highly complementary because data-driven methods are more predictive but less interpretable and robust, while theory-driven methods are more interpretable and robust but less predictive. Using their complementary nature, this study designs a theory-based residual neural network (TB-ResNet) framework, which synergizes discrete choice models (DCMs) and deep neural networks (DNNs) based on their shared utility interpretation. The TB-ResNet framework is simple, as it uses a (δ, 1-δ) weighting to take advantage of DCMs’ simplicity and DNNs’ richness, and to prevent underfitting from the DCMs and overfitting from the DNNs. This framework is also flexible: three instances of TB-ResNets are designed based on multinomial logit model (MNL-ResNets), prospect theory (PT-ResNets), and hyperbolic discounting (HD-ResNets), which are tested on three data sets. Compared to pure DCMs, the TB-ResNets provide greater prediction accuracy and reveal a richer set of behavioral mechanisms owing to the utility function augmented by the DNN component in the TB-ResNets. Compared to pure DNNs, the TB-ResNets can modestly improve prediction and significantly improve interpretation and robustness, because the DCM component in the TB-ResNets stabilizes the utility functions and input gradients. Overall, this study demonstrates that it is both feasible and desirable to synergize DCMs and DNNs by combining their utility specifications under a TB-ResNet framework. Although some limitations remain, this TB-ResNet framework is an important first step to create mutual benefits between DCMs and DNNs for travel behavior modeling, with joint improvement in prediction, interpretation, and robustness." @default.
• W3137266700 created "2021-03-29" @default.
• W3137266700 creator A5023905102 @default.
• W3137266700 creator A5029281894 @default.
• W3137266700 creator A5087622413 @default.
• W3137266700 date "2021-04-01" @default.
• W3137266700 modified "2023-09-30" @default.
• W3137266700 title "Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks" @default.
• W3137266700 cites W1827495041 @default.
• W3137266700 cites W1967444754 @default.
• W3137266700 cites W1975625812 @default.
• W3137266700 cites W1987832219 @default.
• W3137266700 cites W1988115241 @default.
• W3137266700 cites W1988942353 @default.
• W3137266700 cites W1993334657 @default.
• W3137266700 cites W1998503232 @default.
• W3137266700 cites W2008900804 @default.
• W3137266700 cites W2026905436 @default.
• W3137266700 cites W2041946752 @default.
• W3137266700 cites W2044098639 @default.
• W3137266700 cites W2089096972 @default.
• W3137266700 cites W2094104200 @default.
• W3137266700 cites W2100056252 @default.
• W3137266700 cites W2102886298 @default.
• W3137266700 cites W2103496339 @default.
• W3137266700 cites W2126539823 @default.
• W3137266700 cites W2132320742 @default.
• W3137266700 cites W2137983211 @default.
• W3137266700 cites W2148111566 @default.
• W3137266700 cites W2225877176 @default.
• W3137266700 cites W2518496153 @default.
• W3137266700 cites W2529827714 @default.
• W3137266700 cites W2563505101 @default.
• W3137266700 cites W2587802550 @default.
• W3137266700 cites W2593182953 @default.
• W3137266700 cites W2610886376 @default.
• W3137266700 cites W2657631929 @default.
• W3137266700 cites W2782738497 @default.
• W3137266700 cites W2793820729 @default.
• W3137266700 cites W2886622679 @default.
• W3137266700 cites W2897247459 @default.
• W3137266700 cites W2903054425 @default.
• W3137266700 cites W2919115771 @default.
• W3137266700 cites W2958110591 @default.
• W3137266700 cites W2963048283 @default.
• W3137266700 cites W2964319113 @default.
• W3137266700 cites W2969279223 @default.
• W3137266700 cites W2969825018 @default.
• W3137266700 cites W2973461188 @default.
• W3137266700 cites W2974087501 @default.
• W3137266700 cites W2982974789 @default.
• W3137266700 cites W2999712306 @default.
• W3137266700 cites W3004748517 @default.
• W3137266700 cites W3011865677 @default.
• W3137266700 cites W3047663291 @default.
• W3137266700 cites W3121590395 @default.
• W3137266700 cites W3122678879 @default.
• W3137266700 cites W4252707658 @default.
• W3137266700 doi "https://doi.org/10.1016/j.trb.2021.03.002" @default.
• W3137266700 hasPublicationYear "2021" @default.
• W3137266700 type Work @default.
• W3137266700 sameAs 3137266700 @default.
• W3137266700 citedByCount "16" @default.
• W3137266700 countsByYear W31372667002021 @default.
• W3137266700 countsByYear W31372667002022 @default.
• W3137266700 countsByYear W31372667002023 @default.
• W3137266700 crossrefType "journal-article" @default.
• W3137266700 hasAuthorship W3137266700A5023905102 @default.
• W3137266700 hasAuthorship W3137266700A5029281894 @default.
• W3137266700 hasAuthorship W3137266700A5087622413 @default.
• W3137266700 hasBestOaLocation W31372667002 @default.
• W3137266700 hasConcept C104317684 @default.
• W3137266700 hasConcept C11413529 @default.
• W3137266700 hasConcept C119857082 @default.
• W3137266700 hasConcept C126838900 @default.
• W3137266700 hasConcept C154945302 @default.
• W3137266700 hasConcept C155512373 @default.
• W3137266700 hasConcept C183115368 @default.
• W3137266700 hasConcept C185592680 @default.
• W3137266700 hasConcept C22019652 @default.
• W3137266700 hasConcept C2944601119 @default.
• W3137266700 hasConcept C2984842247 @default.
• W3137266700 hasConcept C41008148 @default.
• W3137266700 hasConcept C50644808 @default.
• W3137266700 hasConcept C55493867 @default.
• W3137266700 hasConcept C63479239 @default.
• W3137266700 hasConcept C71924100 @default.
• W3137266700 hasConceptScore W3137266700C104317684 @default.
• W3137266700 hasConceptScore W3137266700C11413529 @default.
• W3137266700 hasConceptScore W3137266700C119857082 @default.
• W3137266700 hasConceptScore W3137266700C126838900 @default.
• W3137266700 hasConceptScore W3137266700C154945302 @default.
• W3137266700 hasConceptScore W3137266700C155512373 @default.
• W3137266700 hasConceptScore W3137266700C183115368 @default.
• W3137266700 hasConceptScore W3137266700C185592680 @default.
• W3137266700 hasConceptScore W3137266700C22019652 @default.
• W3137266700 hasConceptScore W3137266700C2944601119 @default.
• W3137266700 hasConceptScore W3137266700C2984842247 @default.

• next