Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213691922> ?p ?o ?g. }
- W3213691922 abstract "Neural operators can learn nonlinear mappings between function spaces and offer a new simulation paradigm for real-time prediction of complex dynamics for realistic diverse applications as well as for system identification in science and engineering. Herein, we investigate the performance of two neural operators, and we develop new practical extensions that will make them more accurate and robust and importantly more suitable for industrial-complexity applications. The first neural operator, DeepONet, was published in 2019, and the second one, named Fourier Neural Operator or FNO, was published in 2020. In order to compare FNO with DeepONet for realistic setups, we develop several extensions of FNO that can deal with complex geometric domains as well as mappings where the input and output function spaces are of different dimensions. We also endow DeepONet with special features that provide inductive bias and accelerate training, and we present a faster implementation of DeepONet with cost comparable to the computational cost of FNO. We consider 16 different benchmarks to demonstrate the relative performance of the two neural operators, including instability wave analysis in hypersonic boundary layers, prediction of the vorticity field of a flapping airfoil, porous media simulations in complex-geometry domains, etc. The performance of DeepONet and FNO is comparable for relatively simple settings, but for complex geometries and especially noisy data, the performance of FNO deteriorates greatly. For example, for the instability wave analysis with only 0.1% noise added to the input data, the error of FNO increases 10000 times making it inappropriate for such important applications, while there is hardly any effect of such noise on the DeepONet. We also compare theoretically the two neural operators and obtain similar error estimates for DeepONet and FNO under the same regularity assumptions." @default.
- W3213691922 created "2021-11-22" @default.
- W3213691922 creator A5008752991 @default.
- W3213691922 creator A5009658255 @default.
- W3213691922 creator A5014873301 @default.
- W3213691922 creator A5015683810 @default.
- W3213691922 creator A5025814758 @default.
- W3213691922 creator A5030093874 @default.
- W3213691922 creator A5030429211 @default.
- W3213691922 date "2021-11-10" @default.
- W3213691922 modified "2023-10-18" @default.
- W3213691922 title "A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data." @default.
- W3213691922 cites W1533861849 @default.
- W3213691922 cites W1644960119 @default.
- W3213691922 cites W1677182931 @default.
- W3213691922 cites W2037606505 @default.
- W3213691922 cites W2059840714 @default.
- W3213691922 cites W2091178963 @default.
- W3213691922 cites W2103496339 @default.
- W3213691922 cites W2139923370 @default.
- W3213691922 cites W2302501749 @default.
- W3213691922 cites W2400593277 @default.
- W3213691922 cites W2772097715 @default.
- W3213691922 cites W2890968382 @default.
- W3213691922 cites W2919958648 @default.
- W3213691922 cites W2963582035 @default.
- W3213691922 cites W2969381807 @default.
- W3213691922 cites W2972663523 @default.
- W3213691922 cites W3004368638 @default.
- W3213691922 cites W3010501116 @default.
- W3213691922 cites W3010849941 @default.
- W3213691922 cites W3011147100 @default.
- W3213691922 cites W3012417314 @default.
- W3213691922 cites W3014009018 @default.
- W3213691922 cites W3021748939 @default.
- W3213691922 cites W3041682155 @default.
- W3213691922 cites W3043516796 @default.
- W3213691922 cites W3087889215 @default.
- W3213691922 cites W3092923133 @default.
- W3213691922 cites W3098546160 @default.
- W3213691922 cites W3099892132 @default.
- W3213691922 cites W3101398262 @default.
- W3213691922 cites W3104873019 @default.
- W3213691922 cites W3115207133 @default.
- W3213691922 cites W3129610195 @default.
- W3213691922 cites W3133338006 @default.
- W3213691922 cites W3134515731 @default.
- W3213691922 cites W3137240924 @default.
- W3213691922 cites W3137474564 @default.
- W3213691922 cites W3137512151 @default.
- W3213691922 cites W3137898953 @default.
- W3213691922 cites W3146803896 @default.
- W3213691922 cites W3160886682 @default.
- W3213691922 cites W3161792008 @default.
- W3213691922 cites W3161912457 @default.
- W3213691922 cites W3163993681 @default.
- W3213691922 cites W3167256391 @default.
- W3213691922 cites W3186384563 @default.
- W3213691922 cites W3194436063 @default.
- W3213691922 cites W3195252089 @default.
- W3213691922 cites W3195348523 @default.
- W3213691922 cites W3198274547 @default.
- W3213691922 cites W3201108720 @default.
- W3213691922 cites W3208453486 @default.
- W3213691922 cites W3209909540 @default.
- W3213691922 hasPublicationYear "2021" @default.
- W3213691922 type Work @default.
- W3213691922 sameAs 3213691922 @default.
- W3213691922 citedByCount "1" @default.
- W3213691922 countsByYear W32136919222021 @default.
- W3213691922 crossrefType "posted-content" @default.
- W3213691922 hasAuthorship W3213691922A5008752991 @default.
- W3213691922 hasAuthorship W3213691922A5009658255 @default.
- W3213691922 hasAuthorship W3213691922A5014873301 @default.
- W3213691922 hasAuthorship W3213691922A5015683810 @default.
- W3213691922 hasAuthorship W3213691922A5025814758 @default.
- W3213691922 hasAuthorship W3213691922A5030093874 @default.
- W3213691922 hasAuthorship W3213691922A5030429211 @default.
- W3213691922 hasConcept C104317684 @default.
- W3213691922 hasConcept C112124176 @default.
- W3213691922 hasConcept C11413529 @default.
- W3213691922 hasConcept C115961682 @default.
- W3213691922 hasConcept C127413603 @default.
- W3213691922 hasConcept C14036430 @default.
- W3213691922 hasConcept C146978453 @default.
- W3213691922 hasConcept C154945302 @default.
- W3213691922 hasConcept C158448853 @default.
- W3213691922 hasConcept C17020691 @default.
- W3213691922 hasConcept C185592680 @default.
- W3213691922 hasConcept C202444582 @default.
- W3213691922 hasConcept C33923547 @default.
- W3213691922 hasConcept C41008148 @default.
- W3213691922 hasConcept C50644808 @default.
- W3213691922 hasConcept C55493867 @default.
- W3213691922 hasConcept C78458016 @default.
- W3213691922 hasConcept C86339819 @default.
- W3213691922 hasConcept C86803240 @default.
- W3213691922 hasConcept C9652623 @default.
- W3213691922 hasConcept C99498987 @default.
- W3213691922 hasConceptScore W3213691922C104317684 @default.