Mahmoud Qasim Yaseen
College of Engineering
Works (3)
Updated: April 11th, 2024 05:00
2024 journal article
Functional PCA and deep neural networks-based Bayesian inverse uncertainty quantification with transient experimental data
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 420.
author keywords: Bayesian inverse UQ; Functional alignment; Functional PCA; Neural networks
TL;DR:
This work focuses on developing an inverse UQ process for time-dependent responses, using functional principal component analysis (PCA) and deep neural network (DNN)-based surrogate models, and shows an improvement in reducing the dimension of the TRACE transient simulations.
(via Semantic Scholar)
open access via arxiv.org (repository)
Sources: Web Of Science, ORCID, NC State University Libraries
Added: January 25, 2024
2023 journal article
Fast and accurate reduced-order modeling of a MOOSE-based additive manufacturing model with operator learning
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 129(7-8), 3123–3139.
author keywords: Additive manufacturing; Reduced-order modeling; Fourier neural operator; Deep operator network; MOOSE framework
Sources: Web Of Science, NC State University Libraries
Added: April 8, 2024
2022 article
Quantification of Deep Neural Network Prediction Uncertainties for VVUQ of Machine Learning Models
Nuclear Science and Engineering.
author keywords: Uncertainty quantification; Deep Neural Network; Monte Carlo Dropout; Deep Ensemble; Bayesian Neural Network
TL;DR:
Three techniques for UQ of DNNs are compared, namely, Monte Carlo Dropout, Deep Ensembles (DE), and Bayesian Neural Networks (BNNs), and it is found that the three methods typically require different DNN architectures and hyperparameters to optimize their performance.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
11. Sustainable Cities and Communities
(Web of Science)
Sources: Web Of Science, ORCID, NC State University Libraries
Added: November 3, 2022