Skip to main navigation
Skip to search
Skip to main content
Illinois Experts Home
LOGIN & Help
Home
Profiles
Research units
Research & Scholarship
Datasets
Honors
Press/Media
Activities
Search by expertise, name or affiliation
PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
Weiheng Zhong
,
Hadi Meidani
Civil and Environmental Engineering
Biomedical and Translational Sciences
Research output
:
Contribution to journal
›
Article
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Stochastic Differential Equations
100%
Variational Autoencoder
100%
Physics-informed
100%
System Parameters
50%
Inverse Problem
33%
Governing Equation
33%
Neural Network
16%
Performance Improvement
16%
Physics-based
16%
Number of Measurements
16%
Stochastic Processes
16%
Forward Problem
16%
Loss Function
16%
Generative Models
16%
System Variables
16%
Network Parameters
16%
System Solution
16%
Automatic Differentiation
16%
Stochastic Gradient Algorithm
16%
Mixed Problem
16%
Maximum Mean Discrepancy
16%
Wasserstein Generative Adversarial Network
16%
Physics-informed Neural Networks
16%
Performance Network
16%
Engineering
Stochastic Differential
100%
System Parameter
50%
Autoencoder
50%
Limited Number
25%
Generative Model
25%
Network Parameter
25%
Gradient Descent
25%
Loss Function
25%
Mixed Problem
25%
Forward Equation
25%
Physics Informed Neural Network
25%
Physics
Physics
100%
Operators (Mathematics)
100%
Neural Network
28%
Chemical Engineering
Neural Network
100%