Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Advantage of Binary Stochastic synapses for hardware Spiking Neural Networks with realistic memristors

Sulinskas, Karolis and Borg, Mattias LU orcid (2022) In Neuromorphic Computing and Engineering 2.
Abstract
Hardware implementing spiking neural networks (SNNs) has the potential to provide transformative gains in energy efficiency and throughput for energy-restricted machine-learning tasks. This is enabled by large arrays of memristive synapse devices that can be realized by various emerging memory technologies. But in practice, the performance of such hardware is limited by non-ideal features of the memristor devices such as nonlinear and asymmetric state updates, limited bit-resolution, limited cycling endurance and device noise. Here we investigate how stochastic switching in binary synapses can provide advantages compared with realistic analog memristors when using unsupervised training of SNNs via spike timing-dependent plasticity. We find... (More)
Hardware implementing spiking neural networks (SNNs) has the potential to provide transformative gains in energy efficiency and throughput for energy-restricted machine-learning tasks. This is enabled by large arrays of memristive synapse devices that can be realized by various emerging memory technologies. But in practice, the performance of such hardware is limited by non-ideal features of the memristor devices such as nonlinear and asymmetric state updates, limited bit-resolution, limited cycling endurance and device noise. Here we investigate how stochastic switching in binary synapses can provide advantages compared with realistic analog memristors when using unsupervised training of SNNs via spike timing-dependent plasticity. We find that the performance of binary stochastic SNNs is similar to or even better than analog deterministic SNNs when one considers memristors with realistic bit-resolution as well in situations with considerable cycle-to-cycle noise. Furthermore, binary stochastic SNNs require many fewer weight updates to train, leading to superior utilization of the limited endurance in realistic memristive devices. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Neuromorphic Computing and Engineering
volume
2
article number
034008
publisher
IOP Publishing
ISSN
2634-4386
project
Robust neuromorphic computing using ferroelectric memristors
language
English
LU publication?
yes
id
45d6f81d-19c2-4004-9b3f-5f85e7363f5c
date added to LUP
2022-03-11 14:44:37
date last changed
2023-02-28 11:27:20
@article{45d6f81d-19c2-4004-9b3f-5f85e7363f5c,
  abstract     = {{Hardware implementing spiking neural networks (SNNs) has the potential to provide transformative gains in energy efficiency and throughput for energy-restricted machine-learning tasks. This is enabled by large arrays of memristive synapse devices that can be realized by various emerging memory technologies. But in practice, the performance of such hardware is limited by non-ideal features of the memristor devices such as nonlinear and asymmetric state updates, limited bit-resolution, limited cycling endurance and device noise. Here we investigate how stochastic switching in binary synapses can provide advantages compared with realistic analog memristors when using unsupervised training of SNNs via spike timing-dependent plasticity. We find that the performance of binary stochastic SNNs is similar to or even better than analog deterministic SNNs when one considers memristors with realistic bit-resolution as well in situations with considerable cycle-to-cycle noise. Furthermore, binary stochastic SNNs require many fewer weight updates to train, leading to superior utilization of the limited endurance in realistic memristive devices.}},
  author       = {{Sulinskas, Karolis and Borg, Mattias}},
  issn         = {{2634-4386}},
  language     = {{eng}},
  month        = {{08}},
  publisher    = {{IOP Publishing}},
  series       = {{Neuromorphic Computing and Engineering}},
  title        = {{Advantage of Binary Stochastic synapses for hardware Spiking Neural Networks with realistic memristors}},
  url          = {{https://lup.lub.lu.se/search/files/123701187/2022_Sulinskas_Neuromorph._Comput._Eng._2_034008.pdf}},
  volume       = {{2}},
  year         = {{2022}},
}