STAR-seminars: Lyudmila Grigoryeva

Image may contain: Sky, Architecture, Animation.

The webinars will take place on Zoom and a link to the virtual room will be sent out to all those who registered at the registration page.


Speaker: Lyudmila Grigoryeva - University of Konstanz

Title: Discrete-time signatures and randomness in reservoir computing

Abstract: A new explanation of geometric nature of the reservoir computing phenomenon is presented. Reservoir computing is understood in the literature as the possibility of approximating input/output systems with randomly chosen recurrent neural systems and a trained linear readout layer. Light is shed on this phenomenon by constructing what is called strongly universal reservoir systems as random projections of a family of state-space systems that generate Volterra series expansions. This procedure yields a state-affine reservoir system with randomly generated coefficients in a dimension that is logarithmically reduced with respect to the original system. This reservoir system is able to approximate any element in the fading memory filters class just by training a different linear readout for each different filter. Explicit expressions for the probability distributions needed in the generation of the projected reservoir system are stated and bounds for the committed approximation error are provided.


This series of webinars addresses all interested people in probability, stochastic analysis, control, risk evaluation, statistics, with a view towards applications, in particular to renewable energy markets and production. This series brings together the major research themes of the projects STORMSCROLLER, and SPATUS

Published Mar. 9, 2021 9:12 AM - Last modified Apr. 20, 2021 3:01 PM