KIP publications

year 2020
author(s) J. Göltz, A. Baumbach, S. Billaudelle, O. Breitwieser, L. Kriener, A. F. Kungl, K. Meier, J. Schemmel, M. A. Petrovici
title Fast and deep neuromorphic learning with first-spike coding
KIP-Nummer HD-KIP 20-14
KIP-Gruppe(n) F9
document type Paper
Keywords deep learning, analog neuromorphic hardware, spiking neural networks, error backpropagation, time-to-first-spike coding
source NICE 2020
Abstract (en)

For a biological agent operating under environmental pressure, energy consumption and reaction times are of critical importance. Similarly, engineered systems also strive 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. In the time-to-first-spike coding framework, both of these goals are inherently emerging features of learning. Here, we describe a rigorous derivation of error- backpropagation-based learning for hierarchical networks of leaky integrate-and-fire neurons. This narrows the gap between previous existing models of first-spike-time learning and biological neuronal dynamics, thereby also enabling fast and energy-efficient inference on analog neuromorphic devices that inherit these dynamics from their biological archetypes.

  author   = {G\"{o}ltz, J. and Baumbach, A. and Billaudelle, S. and Kungl, A. F. and Breitwieser, O. and Meier, K. and Schemmel, J. and Kriener, L. and Petrovici, M. A.},
  title    = {Fast and Deep Neuromorphic Learning with First-Spike Coding},
  booktitle = {Proceedings of the Neuro-Inspired Computational Elements Workshop},
  year     = {2020},
  volume   = {},
  number   = {14},
  series   = {NICE ’20},
  pages    = {3},
  address  = {New York, NY, USA},
  month    = {3},
  publisher = {Association for Computing Machinery},
  note     = {ISBN: 9781450377188; 10.1145/3381755.3381770}
Sample Image
Datei ttfs_2020_NICE_full
KIP - Bibliothek
Im Neuenheimer Feld 227
Raum 3.402
69120 Heidelberg