KIP publications

year 2021
author(s) J. Göltz, L. Kriener, A. Baumbach, S. Billaudelle, O. Breitwieser, B. Cramer, D. Dold, A. F. Kungl, W. Senn, J. Schemmel, K. Meier, M. A. Petrovici
title Fast and energy-efficient neuromorphic deep learning with first-spike times
KIP-Nummer HD-KIP 21-67
KIP-Gruppe(n) F9
document type Paper
source Nature Machine Intelligence volume 3 (2021) 823–835
doi 10.1038/s42256-021-00388-x
Abstract (en)

For a biological agent operating under environmental pressure, energy consumption and reaction times are of critical importance. Similarly, engineered systems are optimized for short time-to-solution and low energy-to-solution characteristics. At the level of neuronal implementation, this implies achieving the desired results with as few and as early spikes as possible. With time-to-first-spike coding, both of these goals are inherently emerging features of learning. Here, we describe a rigorous derivation of a learning rule for such first-spike times in networks of leaky integrate-and-fire neurons, relying solely on input and output spike times, and show how this mechanism can implement error backpropagation in hierarchical spiking networks. Furthermore, we emulate our framework on the BrainScaleS-2 neuromorphic system and demonstrate its capability of harnessing the system’s speed and energy characteristics. Finally, we examine how our approach generalizes to other neuromorphic platforms by studying how its performance is affected by typical distortive effects induced by neuromorphic substrates.

  author   = {G{\"o}ltz, J and Kriener, L and Baumbach, A and Billaudelle, S and Breitwieser, O and Cramer, B and Dold, D and Kungl, AF and Senn, W and Schemmel, J and Meier, Karlheinz and Petrovici, Mihai A.},
  title    = {Fast and energy-efficient neuromorphic deep learning with first-spike times},
  journal  = {Nature Machine Intelligence},
  year     = {2021},
  volume   = {3},
  pages    = {823-835},
  doi      = {10.1038/s42256-021-00388-x},
  url      = {}
URL arXiv
KIP - Bibliothek
Im Neuenheimer Feld 227
Raum 3.402
69120 Heidelberg