A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware

Arjun Rao, Philipp Plank, Andreas Wild, Wolfgang Maass*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Spike-based neuromorphic hardware holds promise for more energy-efficient implementations of deep neural networks (DNNs) than standard hardware such as GPUs. But this requires us to understand how DNNs can be emulated in an event-based sparse firing regime, as otherwise the energy advantage is lost. In particular, DNNs that solve sequence processing tasks typically employ long short-term memory units that are hard to emulate with few spikes. We show that a facet of many biological neurons, slow after-hyperpolarizing currents after each spike, provides an efficient solution. After-hyperpolarizing currents can easily be implemented in neuromorphic hardware that supports multi-compartment neuron models, such as Intel’s Loihi chip. Filter approximation theory explains why after-hyperpolarizing neurons can emulate the function of long short-term memory units. This yields a highly energy-efficient approach to time-series classification. Furthermore, it provides the basis for an energy-efficient implementation of an important class of large DNNs that extract relations between words and sentences in order to answer questions about the text.
Original languageEnglish
Pages (from-to)467-479
Number of pages13
JournalNature Machine Intelligence
Issue number5
Publication statusPublished - May 2022

ASJC Scopus subject areas

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

Fields of Expertise

  • Information, Communication & Computing


Dive into the research topics of 'A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware'. Together they form a unique fingerprint.

Cite this