Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286768460> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4286768460 abstract "Physical modeling is critical for many modern science and engineering applications. From a data science or machine learning perspective, where more domain-agnostic, data-driven models are pervasive, physical knowledge -- often expressed as differential equations -- is valuable in that it is complementary to data, and it can potentially help overcome issues such as data sparsity, noise, and inaccuracy. In this work, we propose a simple, yet powerful and general framework -- AutoIP, for Automatically Incorporating Physics -- that can integrate all kinds of differential equations into Gaussian Processes (GPs) to enhance prediction accuracy and uncertainty quantification. These equations can be linear or nonlinear, spatial, temporal, or spatio-temporal, complete or incomplete with unknown source terms, and so on. Based on kernel differentiation, we construct a GP prior to sample the values of the target function, equation-related derivatives, and latent source functions, which are all jointly from a multivariate Gaussian distribution. The sampled values are fed to two likelihoods: one to fit the observations, and the other to conform to the equation. We use the whitening method to evade the strong dependency between the sampled function values and kernel parameters, and we develop a stochastic variational learning algorithm. AutoIP shows improvement upon vanilla GPs in both simulation and several real-world applications, even using rough, incomplete equations." @default.
- W4286768460 created "2022-07-23" @default.
- W4286768460 creator A5004039295 @default.
- W4286768460 creator A5011744292 @default.
- W4286768460 creator A5024663093 @default.
- W4286768460 creator A5033006662 @default.
- W4286768460 creator A5049020441 @default.
- W4286768460 creator A5052267876 @default.
- W4286768460 date "2022-02-24" @default.
- W4286768460 modified "2023-09-24" @default.
- W4286768460 title "AutoIP: A United Framework to Integrate Physics into Gaussian Processes" @default.
- W4286768460 doi "https://doi.org/10.48550/arxiv.2202.12316" @default.
- W4286768460 hasPublicationYear "2022" @default.
- W4286768460 type Work @default.
- W4286768460 citedByCount "0" @default.
- W4286768460 crossrefType "posted-content" @default.
- W4286768460 hasAuthorship W4286768460A5004039295 @default.
- W4286768460 hasAuthorship W4286768460A5011744292 @default.
- W4286768460 hasAuthorship W4286768460A5024663093 @default.
- W4286768460 hasAuthorship W4286768460A5033006662 @default.
- W4286768460 hasAuthorship W4286768460A5049020441 @default.
- W4286768460 hasAuthorship W4286768460A5052267876 @default.
- W4286768460 hasBestOaLocation W42867684601 @default.
- W4286768460 hasConcept C11413529 @default.
- W4286768460 hasConcept C114614502 @default.
- W4286768460 hasConcept C119857082 @default.
- W4286768460 hasConcept C121332964 @default.
- W4286768460 hasConcept C14036430 @default.
- W4286768460 hasConcept C158622935 @default.
- W4286768460 hasConcept C163716315 @default.
- W4286768460 hasConcept C28826006 @default.
- W4286768460 hasConcept C33923547 @default.
- W4286768460 hasConcept C41008148 @default.
- W4286768460 hasConcept C51167844 @default.
- W4286768460 hasConcept C51955184 @default.
- W4286768460 hasConcept C61326573 @default.
- W4286768460 hasConcept C62520636 @default.
- W4286768460 hasConcept C7218915 @default.
- W4286768460 hasConcept C74193536 @default.
- W4286768460 hasConcept C78458016 @default.
- W4286768460 hasConcept C81692654 @default.
- W4286768460 hasConcept C86803240 @default.
- W4286768460 hasConceptScore W4286768460C11413529 @default.
- W4286768460 hasConceptScore W4286768460C114614502 @default.
- W4286768460 hasConceptScore W4286768460C119857082 @default.
- W4286768460 hasConceptScore W4286768460C121332964 @default.
- W4286768460 hasConceptScore W4286768460C14036430 @default.
- W4286768460 hasConceptScore W4286768460C158622935 @default.
- W4286768460 hasConceptScore W4286768460C163716315 @default.
- W4286768460 hasConceptScore W4286768460C28826006 @default.
- W4286768460 hasConceptScore W4286768460C33923547 @default.
- W4286768460 hasConceptScore W4286768460C41008148 @default.
- W4286768460 hasConceptScore W4286768460C51167844 @default.
- W4286768460 hasConceptScore W4286768460C51955184 @default.
- W4286768460 hasConceptScore W4286768460C61326573 @default.
- W4286768460 hasConceptScore W4286768460C62520636 @default.
- W4286768460 hasConceptScore W4286768460C7218915 @default.
- W4286768460 hasConceptScore W4286768460C74193536 @default.
- W4286768460 hasConceptScore W4286768460C78458016 @default.
- W4286768460 hasConceptScore W4286768460C81692654 @default.
- W4286768460 hasConceptScore W4286768460C86803240 @default.
- W4286768460 hasLocation W42867684601 @default.
- W4286768460 hasOpenAccess W4286768460 @default.
- W4286768460 hasPrimaryLocation W42867684601 @default.
- W4286768460 hasRelatedWork W145098650 @default.
- W4286768460 hasRelatedWork W2031451094 @default.
- W4286768460 hasRelatedWork W2120670437 @default.
- W4286768460 hasRelatedWork W2142075636 @default.
- W4286768460 hasRelatedWork W2384408398 @default.
- W4286768460 hasRelatedWork W2619336040 @default.
- W4286768460 hasRelatedWork W3217770377 @default.
- W4286768460 hasRelatedWork W4225835446 @default.
- W4286768460 hasRelatedWork W4312290701 @default.
- W4286768460 hasRelatedWork W2183680581 @default.
- W4286768460 isParatext "false" @default.
- W4286768460 isRetracted "false" @default.
- W4286768460 workType "article" @default.