Parameter Subset Selection and Active Subspace Techniques for Engineering and Biological Models
Offered By: Inside Livermore Lab via YouTube
Course Description
Overview
Explore techniques for isolating influential parameters in engineering and biological models through this comprehensive webinar. Learn about global sensitivity analysis, parameter subset selection, and active subspace techniques as alternatives for identifying key inputs. Discover how Bayesian calibration on active subspaces can quantify uncertainties in physical parameters. Examine real-world applications in nuclear power plant design, quantitative systems pharmacology, and transductive materials. Gain insights from Distinguished University Professor Ralph C. Smith as he shares his expertise in mathematical modeling of smart material systems, numerical analysis, and uncertainty quantification for physical and biological systems.
Syllabus
Introduction
Who we are
Applications
Neutron Transport Equation
Disease Model
Brain Model
Elementary Applications
VarianceBased Analysis
Multiindex Notation
What Went Wrong
How Do We Address This
Motivation
Intuition
History
Derivative Approximations
Questions
Limitations
Verification
Reference
Adaptive Step Size
Active Subspaces
Monte Carlo Sampling
Nuclear Example
Nuclear Example Results
Bayesian Inference
Bayesian Inference Example
Activity Scores
Active Subspace
Conclusions
Taught by
Inside Livermore Lab
Related Courses
Data Science: Inferential Thinking through SimulationsUniversity of California, Berkeley via edX Decision Making Under Uncertainty: Introduction to Structured Expert Judgment
Delft University of Technology via edX Probabilistic Deep Learning with TensorFlow 2
Imperial College London via Coursera Agent Based Modeling
The National Centre for Research Methods via YouTube Sampling in Python
DataCamp