Reservoir Computing based on Delay-dynamical Systems

• Talk

• Lennert Appeltant
• Vrije Universiteit, Brussels, Belgium
• 19 de julio de 2012 a las 11:30
• IFISC Seminar Room
• Announcement file

Ver en youtube Ver video localmente

Today, except for mathematical operations, our brain functions much faster and more efficient than any supercomputer. It is precisely this form of information processing in neural networks that inspires researchers to create systems that mimic the brain’s information processing capabilities. We propose a novel approach to implement these alternative computer architectures, based on delayed feedback. We show that one single nonlinear node with delayed feedback can replace a large network of nonlinear nodes.

First we numerically investigate the architecture and performance of delayed feedback systems as information processing units. Then we elaborate on electronic and opto-electronic implementations of the concept. Next to evaluating their performance for standard benchmarks, we also study task independent properties of the system, extracting information on how to further improve the initial scheme. Finally, some simple modifications are suggested, yielding improvements in terms of speed or performance.

Detalles de contacto:

Manuel Matías

Contact form