Original Research ARTICLE

Front. Neurosci., 17 July 2012 | doi: 10.3389/fnins.2012.00090

Is a 4-bit synaptic weight resolution enough? – constraints on enabling spike-timing dependent plasticity in neuromorphic hardware

  • 1 Kirchhoff Institute for Physics, Ruprecht-Karls-University Heidelberg, Heidelberg, Germany
  • 2 Computational and Systems Neuroscience (INM-6), Institute of Neuroscience and Medicine, Research Center Jülich, Jülich, Germany
  • 3 Brain and Neural Systems Team, RIKEN Computational Science Research Program, Wako-shi, Japan
  • 4 RIKEN Brain Science Institute, Wako-shi, Japan
  • 5 RWTH Aachen University, Aachen, Germany

Large-scale neuromorphic hardware systems typically bear the trade-off between detail level and required chip resources. Especially when implementing spike-timing dependent plasticity, reduction in resources leads to limitations as compared to floating point precision. By design, a natural modification that saves resources would be reducing synaptic weight resolution. In this study, we give an estimate for the impact of synaptic weight discretization on different levels, ranging from random walks of individual weights to computer simulations of spiking neural networks. The FACETS wafer-scale hardware system offers a 4-bit resolution of synaptic weights, which is shown to be sufficient within the scope of our network benchmark. Our findings indicate that increasing the resolution may not even be useful in light of further restrictions of customized mixed-signal synapses. In addition, variations due to production imperfections are investigated and shown to be uncritical in the context of the presented study. Our results represent a general framework for setting up and configuring hardware-constrained synapses. We suggest how weight discretization could be considered for other backends dedicated to large-scale simulations. Thus, our proposition of a good hardware verification practice may rise synergy effects between hardware developers and neuroscientists.

Keywords: neuromorphic hardware, wafer-scale integration, large-scale spiking neural networks, spike-timing dependent plasticity, synaptic weight resolution, circuit variations, PyNN, NEST

Citation: Pfeil T, Potjans TC, Schrader S, Potjans W, Schemmel J, Diesmann M and Meier K (2012) Is a 4-bit synaptic weight resolution enough? – constraints on enabling spike-timing dependent plasticity in neuromorphic hardware. Front. Neurosci. 6:90. doi: 10.3389/fnins.2012.00090

Received: 27 January 2012; Accepted: 04 June 2012;
Published online: 17 July 2012.

Edited by:

Stefano Fusi, Columbia University, USA

Reviewed by:

Florentin Wörgötter, University Goettingen, Germany

Copyright: © 2012 Pfeil, Potjans, Schrader, Potjans, Schemmel, Diesmann and Meier. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in other forums, provided the original authors and source are credited and subject to any copyright notices concerning any third-party graphics etc.

*Correspondence: Thomas Pfeil, Kirchhoff Institute for Physics, Ruprecht-Karls-University Heidelberg, Im Neuenheimer Feld 227, 69120 Heidelberg, Germany. e-mail: thomas.pfeil@kip.uni-heidelberg.de

Back to top