Graduiertenschule "Entscheidungswissenschaften"

Workshop on Dynamical Systems and Brain-inspired Information Processing

Donnerstag, 05. Oktober 2017
– Freitag, 06. Oktober 2017


Lyudmila Grigoryeva (Universität Konstanz, Germany)

This workshop focuses on data-driven approaches to machine/statistical learning  based on exploiting dynamical systems, sometimes brain-inspired, to perform complex computational and information processing tasks.  Various mathematical connections have already been established between dynamical systems and the classical concept of Turing computability, but it is not clear whether this notion is the most adequate  from a dynamical systems perspective.

This workshop will explore mathematical, algorithmical, neuro-computational, and physical-realization aspects of information processing dynamical systems. The aim is to gather researchers interested in these topics and to seed discussions (and possible future collaborations) between machine/statistical learners,  computational neuroscientists, and microprocessor physicists in Europe.

Contributions to the workshop are invited to cover topics including:

  • nonlinear dynamical systems and phenomena that can be used for information processing and storing
  • reservoir computing approaches
  • novel energy-efficient neuromorphic microchip technologies
  • re-defining "computing" for analog, parallel, unclocked devices
  • the challenge of low-precision and large device mismatch
  • natural neural systems

The workshop is the third in a series with this name. The first two were held in 2012 and 2015 in Besançon (France).