...: zzanjani@uci.edu 1 Corresponding author. Email: raminb@uci.edu 08 06 2023 28 09 2023 29 09 2023 06 08 2024 anomaly detection manifold learning novelty detection Gaussian process uncertainty quantification autoencoder artificial intelligence data-driven...

...-lernout@univ-eiffel.fr Email: olivier.ezvan@univ-eiffel.fr 1 Corresponding author. Email: christian.soize@univ-eiffel.fr 19 01 2024 03 04 2024 04 04 2024 09 05 2024 Graphical Abstract Figure probabilistic learning uncertainty quantification nonlinear...

... [26] Ravi , S. K. , Bhaduri , A. , Amer , A. , Ghosh , S. , Wang , L. , Hoffman , A. , and Umretiya , R. , 2023 , “ On Uncertainty Quantification in Materials Modeling and Discovery: Applications of GE’s BHM and IDACE ,” AIAA SCITECH 2023 Forum , National Harbor, MD...

... artificial intelligence physics-based simulation uncertainty quantification physics-constrained neural network Bayesian neural network dual-dimer method machine learning for engineering applications Neural networks are effective tools to build surrogate models of complex systems to approximate...

... are aleatory (due to natural variability) and some are epistemic (due to lack of knowledge). Uncertainty quantification (UQ) seeks to quantify the uncertainty in the model prediction arising from multiple, heterogeneous sources. UQ has two directions: the forward problem and the inverse problem...

... heterogeneity. Fig. 5 Illustration of CVaR Q ¯ α ( λ ( x , ζ ) ) at x = [4.53 × 10 3 , 2.22 × 10 −1 ] Illustration of CVaR Q¯α(λ(x,ζ)) at x = [4.53 × 103, 2.22 × 10−1] CVaR is widely used in uncertainty quantification [ 54 – 56 ], and we adopt this concept to ensure...

...-driven engineering uncertainty quantification inverse methods for engineering applications machine learning for engineering applications 30 07 2021 04 11 2021 05 11 2021 10 12 2021 Contributed by the Computers and Information Division of ASME for publication in the J...

... uncertainty quantification (UQ) method. In the ETSPM, the subinterval perturbation method (SIPM) is introduced to decompose original FE into several small subintervals. By comparing results yielded by the ETIPM and ETSPM with those by the evidence theory-based Monte Carlo method (ETMCM), numerical examples...