CURRENT: 12.S592 U/G MIT REGISTRATION Lec: F. 9-11 Rm: Zoom & 54-1827
Simultaneously offered at Instituto Politecnico National (IPN) Queretaro (via Zoom).
Instructor: Sai Ravela (ravela@mit.edu)
- Offered since 2017, in earlier form since 2013
- Dynamics, Optimization, and Information foundations of Machine Learning
- ML-based System Dynamics and Optimization for Earth, Planets, Climate, and Life
- Flexible participation model
- Pre-reqs: Linear Algebra, Probability & Stat, a first course in ML, and some Systems preparation (at least one of) Statistical Signal Processing, Estimation, Control or Optimization
Seminar course 12.S592 is offered every term. Its syllabus follows four primary themes annually with an almost periodic, ahem, “50-shades of challenging grey matter” over approximately 50 weeks. Some have stayed on in the course for six years!
Theme By Season
-
The role of DOLS in some applications are investigated by participant interest (this is a variable and generally growing list).
- Co-Active Surrogates for Earth, Planets, Climate, and Life.
- Inverse Problems: Exoplanet Atmospheric Retrieval, Seismic Monitoring, Geothermal energy.
- Model-based Estimation: Uncertainty Quantification and Data Assimilation.
- Detection: Exoplanet Detection and Search.
- Control: Nonlinear Model Predictive Control of Autonomous Aircraft Systems.
- Scaling Laws & Diffusion Processes for Downscaling and Super-resolution. We want to understand scaling behavior using Neuro-Physical representations and simulate high-resolution physics from low-resolution inputs.
- Discovering Dynamics: From Operators to Oscillators. Applications: Weather extremes and Climate. Special application to learning reduced coherent fluid models such as jets and plumes.
- Optimal Mapping: e.g., exposure mapping for risk, plume-mapping using autonomous aircraft.
- Chaining Uncertainty and Extremes. Applications: Cyclone-induced risk assessment.
- Modeling Interactions in Many-Body Systems. Applications: Density Functional Theory (DFT) and computational spectroscopy (new).
- Serious Games and Multi-Agent Systems. Applications: Sustainable Agriculture (new).
- Stochastic Modeling. Applications: Stochastic models for extratropical cyclones and non-Gaussian fluids.
- Retrieval Augmented Generative Modeling. Applications: Vulnerability mapping.
- Relevance Feedback in Image Recognition: e.g., Fine-grained recognition for individual identification in conservation.