Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes

Christoph Stöckl, Wolfgang Maass*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Spike-based neuromorphic hardware promises to reduce the energy consumption of image classification and other deep-learning applications, particularly on mobile phones and other edge devices. However, direct training of deep spiking neural networks is difficult, and previous methods for converting trained artificial neural networks to spiking neurons were inefficient because the neurons had to emit too many spikes. We show that a substantially more efficient conversion arises when one optimizes the spiking neuron model for that purpose, so that it not only matters for information transmission how many spikes a neuron emits, but also when it emits those spikes. This advances the accuracy that can be achieved for image classification with spiking neurons, and the resulting networks need on average just two spikes per neuron for classifying an image. In addition, our new conversion method improves latency and throughput of the resulting spiking networks.
Original languageEnglish
Pages (from-to)230-238
Number of pages9
JournalNature Machine Intelligence
Volume3
Issue number3
DOIs
Publication statusPublished - 11 Mar 2021

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes'. Together they form a unique fingerprint.

Cite this