Blog
About

10
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          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.

          Related collections

          Most cited references 40

          • Record: found
          • Abstract: found
          • Article: not found

          Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs.

          Activity-driven modifications in synaptic connections between neurons in the neocortex may occur during development and learning. In dual whole-cell voltage recordings from pyramidal neurons, the coincidence of postsynaptic action potentials (APs) and unitary excitatory postsynaptic potentials (EPSPs) was found to induce changes in EPSPs. Their average amplitudes were differentially up- or down-regulated, depending on the precise timing of postsynaptic APs relative to EPSPs. These observations suggest that APs propagating back into dendrites serve to modify single active synaptic connections, depending on the pattern of electrical activity in the pre- and postsynaptic neurons.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Matching properties of MOS transistors

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              The blue brain project.

               Henry Markram (2006)
              IBM's Blue Gene supercomputer allows a quantum leap in the level of detail at which the brain can be modelled. I argue that the time is right to begin assimilating the wealth of data that has been accumulated over the past century and start building biologically accurate models of the brain from first principles to aid our understanding of brain function and dysfunction.
                Bookmark

                Author and article information

                Journal
                2012-01-30
                2012-08-14
                Article
                10.3389/fnins.2012.00090
                1201.6255

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                Custom metadata
                Front. Neurosci. 6:90 (2012)
                q-bio.NC

                Neurosciences

                Comments

                Comment on this article