Classification and regression of spatio-temporal signals using NeuCube and its realization on SpiNNaker neuromorphic hardware.

Journal: Journal of neural engineering
Published Date: Dec 21, 2018

Abstract

OBJECTIVE: The objective of this work is to use the capability of spiking neural networks to capture the spatio-temporal information encoded in time-series signals and decode them without the use of hand-crafted features and vector-based learning and the realization of the spiking model on low-power neuromorphic hardware.

Authors

  • Jan Behrenbeck
    Department of Mechanical Engineering, Technical University of Munich, Munich, Germany.
  • Zied Tayeb
  • Cyrine Bhiri
  • Christoph Richter
  • Oliver Rhodes
  • Nikola Kasabov
    Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland 1010, New Zealand. Electronic address: nkasabov@aut.ac.nz.
  • Josafath I Espinosa-Ramos
  • Steve Furber
    School of Computer Science, APT Group, University of Manchester, Manchester M13 9PL, U.K. steve.furber@manchester.ac.uk.
  • Gordon Cheng
    Technische Universität München, Institute for Cognitive Systems, Arcisstraße 21, 80333 München, Germany.
  • Jörg Conradt
    Neuroscientific System Theory (NST), Department of Electrical Engineering and Information Technology, Technische Universität München (TUM), Karlstraße 45, 80333 München, Germany. Electronic address: conradt@tum.de.

Keywords

External Resources

Popular Topics
Recent Journals