Reservoir Computing and the Learning of Dynamic Processes
Speaker
Juan-Pablo Ortega, Nanyang Technological University
Time
2021-11-23 14:00 ~ 15:00, in 3 days (Asia/Shanghai Time)
Venue
ZOOM--APP
Zoom Info
Link:
https://ntu-sg.zoom.us/j/96269196055 Meeting ID: 962 6919 6055
Passcode: 917685
Abstract
Dynamic processes regulate the behaviour of virtually any artificial and biological agent, from stock markets to epidemics, from driverless cars to healthcare robots. The problem of modeling, forecasting, and generally speaking learning dynamic processes is one of the most classical, sophisticated, and strategically significant problems in the natural and the social sciences. In this talk we shall discuss both classical and recent results on the modeling and learning of dynamical systems and input/output systems using an approach generically known as reservoir computing. This information processing framework is characterized by the use of cheap-to-train randomly generated state-space systems for which promising high-performance physical realizations with dedicated hardware have been proposed in recent years. In our presentation we shall put a special emphasis in the approximation properties of these constructions.
Bio
Juan-Pablo Ortega is a Professor of Applied Geometry and Dynamics at the Division of Mathematical Sciences of the Nanyang Technological University in Singapore. He holds a first degree in Theoretical Physics from the Universidad de Zaragoza (Spain), a Masters and a PhD in Mathematics from the University of California, Santa Cruz, and a Habilitation degree from the Université de Nice (France). After a postdoc at the Ecole Polytechnique Fédérale de Lausanne (Switzerland), he became a researcher at the Centre Nationale de la Recherche Scientifique (CNRS, France). Before joining NTU Singapore, he taught mathematics at the Université Bourgogne Franche-Comté (France) and the University of St. Gallen (Switzerland).
Prof. Ortega is a mathematician working on the learning and statistical modeling of dynamic processes like input/output systems, stochastic processes, dynamical and controlled systems, and time series. He is also interested in the applications of these topics to financial econometrics, mathematical finance, physiological signal treatment, and engineering. He has worked extensively in geometric mechanics, where he focuses on stability theory, symmetric systems, and their reduction.
--
FROM 202.121.181.*