Data Driven Learning and Control seminar series is organized by the Information and Decision Science Lab at Cornell University and aims to explore the latest advancements and interdisciplinary approaches to data-driven learning and control systems.
Watch on YouTube Live
Stable Adaptation and Learning
While we may soon have AI-based artists or scientists, we are nowhere near autonomous robot plumbers. The human brain still largely outperforms robotic algorithms in most tasks, using computational elements 7 orders of magnitude slower than their artificial counterparts. Similarly, current large scale machine learning algorithms require millions of examples and close proximity to power plants, compared to the brain’s few examples and 20W consumption. We study how modern nonlinear systems tools, such as contraction analysis, virtual dynamical systems, and adaptive nonlinear control can yield quantifiable insights about collective computation and learning in large physical systems and dynamical networks. For instance, we show how stable implicit sparse regularization can be exploited online in adaptive prediction or control to select relevant dynamic models out of plausible physically-based candidates, and how most elementary results on gradient descent and optimization based on convexity can be replaced by much more general results based on Riemannian contraction.
Time permitting, we will also introduce briefly a new approach to neural network architecture directly inspired by astrocyte biology. The approach creates a computational continuum to be explored between dense associative memories and transformers, and may be the first contribution to AI of neuroscience results from the last 50 years.
Bio: Jean-Jacques Slotine is professor of mechanical engineering and information sciences, and brain and cognitive sciences and director of the Nonlinear Systems Laboratory at the Massachusetts Institute of Technology. He received his Ph.D. in estimation and control from MIT in 1983, at age 23. After working at Bell Labs in the computer research department, he joined the faculty at MIT in 1984. Slotine teaches and conducts research in the areas of dynamic systems, robotics, control theory, computational neuroscience, and systems biology.
Research in Slotine’s laboratory focuses on developing rigorous but practical tools for nonlinear systems analysis and control. These have included key advances and experimental demonstrations in the contexts of sliding control, adaptive nonlinear control, adaptive robotics, machine learning, and contraction analysis of nonlinear dynamical systems.
Slotine is the co-author of two popular graduate textbooks, “Robot Analysis and Control” (Asada and Slotine, Wiley, 1986), and “Applied Nonlinear Control” (Slotine and Li, Prentice-Hall, 1991) and is one of the most cited researchers in both systems science and robotics. He was a member of the French National Science Council from 1997 to 2002, and a member of Singapore’s A*STAR SigN Advisory Board from 2007 to 2010. He is currently a member ofthe Scientific Advisory Board of the Italian Institute of Technology. He has held Invited Professor positions at College de France, Ecole Polytechnique, Ecole Normale Superieure, Universita di Roma La Sapienza, and ETH Zurich.