MIT

dols

Dynamics Optimization and Learning Systems

12.S592

  • 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

  • We study a co-active approach to systems theory to infer, estimate, control, learn, or optimize by adapting or selecting data, models, theories, and experts to maximize information gain. These dual feedback loops produce co-active subsystems, each tuning from the other. We posit that this approach is a fundamental mechanism for knowledge acquistion and is consistent with many other theories, including active learning, relevance feedback, incremental online learning, dynamic data-driven systems etc. but unifies them into a single approach that surprisingly has an ancient basis in the Vedic Pramanas.