The Science of Learning from Observations- Leveraging Scientific Computation with Intrinsic Machine Learning Models and Lifelong Learning
Abstract
Complex physical systems exhibit nonlinear, multi-scale, high-dimensional dynamics that challenge current methods of modeling, simulation and interpretability. We will study these issues with ideas and techniques in machine learning, both new and existing but not currently used in this context. We will introduce novel machine learning algorithms that synthesize (and, at times, invent new) fundamental structures in complex dynamical systems from partial observations and different sensor modalities, integrate physical constraints and boundary conditions, accumulate knowledge over observations of multiple dynamical systems and transfer it appropriately to new systems, and link them with computational technology
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Mar 07, 2023
- Source ID
- FA95502110317
Entities
People
- Mauro Maggioni
Organizations
- Air Force Office of Scientific Research
- Johns Hopkins University
- United States Air Force