Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385484583> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4385484583 abstract "Physics-informed neural networks (PINN s) are a newly emerging research frontier in machine learning, which incorporate certain physical laws that govern a given data set, e.g., those described by partial differential equations (PDEs), into the training of the neural network (NN) based on such a data set. In PINN s, the NN acts as the solution approximator for the PDE while the PDE acts as the prior knowledge to guide the NN training, leading to the desired generalization performance of the NN when facing the limited availability of training data. However, training PINNs is a non-trivial task largely due to the complexity of the loss composed of both NN and physical law parts. In this work, we propose a new PINN training framework based on the multi-task optimization (MTO) paradigm. Under this framework, multiple auxiliary tasks are created and solved together with the given (main) task, where the useful knowledge from solving one task is transferred in an adaptive mode to assist in solving some other tasks, aiming to uplift the performance of solving the main task. We implement the proposed framework and apply it to train the PINN for addressing the traffic density prediction problem. Experimental results demonstrate that our proposed training framework leads to significant performance improvement in comparison to the traditional way of training the PINN." @default.
- W4385484583 created "2023-08-03" @default.
- W4385484583 creator A5006614329 @default.
- W4385484583 creator A5011784828 @default.
- W4385484583 creator A5025844181 @default.
- W4385484583 creator A5059128645 @default.
- W4385484583 creator A5063743712 @default.
- W4385484583 creator A5087297482 @default.
- W4385484583 date "2023-06-18" @default.
- W4385484583 modified "2023-10-06" @default.
- W4385484583 title "Training Physics- Informed Neural Networks via Multi-Task Optimization for Traffic Density Prediction" @default.
- W4385484583 cites W1965900320 @default.
- W4385484583 cites W2029465969 @default.
- W4385484583 cites W2066671570 @default.
- W4385484583 cites W2413527939 @default.
- W4385484583 cites W2730438699 @default.
- W4385484583 cites W2763433602 @default.
- W4385484583 cites W2795982117 @default.
- W4385484583 cites W2899283552 @default.
- W4385484583 cites W2967912081 @default.
- W4385484583 cites W3003922491 @default.
- W4385484583 cites W3012417314 @default.
- W4385484583 cites W3034368386 @default.
- W4385484583 cites W3047001618 @default.
- W4385484583 cites W3090337104 @default.
- W4385484583 cites W3129051607 @default.
- W4385484583 cites W3163993681 @default.
- W4385484583 cites W3196004889 @default.
- W4385484583 cites W3199139896 @default.
- W4385484583 cites W4285109022 @default.
- W4385484583 cites W4312771865 @default.
- W4385484583 doi "https://doi.org/10.1109/ijcnn54540.2023.10191301" @default.
- W4385484583 hasPublicationYear "2023" @default.
- W4385484583 type Work @default.
- W4385484583 citedByCount "0" @default.
- W4385484583 crossrefType "proceedings-article" @default.
- W4385484583 hasAuthorship W4385484583A5006614329 @default.
- W4385484583 hasAuthorship W4385484583A5011784828 @default.
- W4385484583 hasAuthorship W4385484583A5025844181 @default.
- W4385484583 hasAuthorship W4385484583A5059128645 @default.
- W4385484583 hasAuthorship W4385484583A5063743712 @default.
- W4385484583 hasAuthorship W4385484583A5087297482 @default.
- W4385484583 hasBestOaLocation W43854845832 @default.
- W4385484583 hasConcept C119857082 @default.
- W4385484583 hasConcept C121332964 @default.
- W4385484583 hasConcept C127413603 @default.
- W4385484583 hasConcept C134306372 @default.
- W4385484583 hasConcept C153294291 @default.
- W4385484583 hasConcept C154945302 @default.
- W4385484583 hasConcept C177148314 @default.
- W4385484583 hasConcept C177264268 @default.
- W4385484583 hasConcept C199360897 @default.
- W4385484583 hasConcept C201995342 @default.
- W4385484583 hasConcept C2777211547 @default.
- W4385484583 hasConcept C2780451532 @default.
- W4385484583 hasConcept C33923547 @default.
- W4385484583 hasConcept C41008148 @default.
- W4385484583 hasConcept C50644808 @default.
- W4385484583 hasConcept C51632099 @default.
- W4385484583 hasConceptScore W4385484583C119857082 @default.
- W4385484583 hasConceptScore W4385484583C121332964 @default.
- W4385484583 hasConceptScore W4385484583C127413603 @default.
- W4385484583 hasConceptScore W4385484583C134306372 @default.
- W4385484583 hasConceptScore W4385484583C153294291 @default.
- W4385484583 hasConceptScore W4385484583C154945302 @default.
- W4385484583 hasConceptScore W4385484583C177148314 @default.
- W4385484583 hasConceptScore W4385484583C177264268 @default.
- W4385484583 hasConceptScore W4385484583C199360897 @default.
- W4385484583 hasConceptScore W4385484583C201995342 @default.
- W4385484583 hasConceptScore W4385484583C2777211547 @default.
- W4385484583 hasConceptScore W4385484583C2780451532 @default.
- W4385484583 hasConceptScore W4385484583C33923547 @default.
- W4385484583 hasConceptScore W4385484583C41008148 @default.
- W4385484583 hasConceptScore W4385484583C50644808 @default.
- W4385484583 hasConceptScore W4385484583C51632099 @default.
- W4385484583 hasLocation W43854845831 @default.
- W4385484583 hasLocation W43854845832 @default.
- W4385484583 hasOpenAccess W4385484583 @default.
- W4385484583 hasPrimaryLocation W43854845831 @default.
- W4385484583 hasRelatedWork W2166162971 @default.
- W4385484583 hasRelatedWork W2346074333 @default.
- W4385484583 hasRelatedWork W2605047975 @default.
- W4385484583 hasRelatedWork W2984272647 @default.
- W4385484583 hasRelatedWork W3176808018 @default.
- W4385484583 hasRelatedWork W3193088696 @default.
- W4385484583 hasRelatedWork W3201070945 @default.
- W4385484583 hasRelatedWork W4287794335 @default.
- W4385484583 hasRelatedWork W4288025908 @default.
- W4385484583 hasRelatedWork W4323767780 @default.
- W4385484583 isParatext "false" @default.
- W4385484583 isRetracted "false" @default.
- W4385484583 workType "article" @default.