Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Sparse distributed memory using N-of-M codes.

Steve B Furber1, W John Bainbridge, J Mike Cumpstey

  • 1Department of Computer Science, The University of Manchester, Oxford Road, Manchester M13 9PL, UK. sfurber@cs.man.ac.uk

Neural Networks : the Official Journal of the International Neural Network Society
|November 16, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Error driven synapse augmented neurogenesis.

Frontiers in artificial intelligence·2022
Same author

Comparison of Artificial and Spiking Neural Networks on Digital Hardware.

Frontiers in neuroscience·2021
Same author

Real-time cortical simulation on neuromorphic hardware.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2019
Same author

SpiNNTools: The Execution Engine for the SpiNNaker Platform.

Frontiers in neuroscience·2019
Same author

sPyNNaker: A Software Package for Running PyNN Simulations on SpiNNaker.

Frontiers in neuroscience·2018
Same author

Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype.

Frontiers in neuroscience·2018
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a novel spiking neural network model for sparse distributed memory (SDM). The enhanced SDM demonstrates efficient storage and scalability for artificial intelligence applications.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Memory Systems

Background:

  • Sparse Distributed Memory (SDM) models, like Kanerva's, offer a theoretical framework for associative memory.
  • Implementing SDM with spiking neurons presents challenges in network architecture and learning rules.

Purpose of the Study:

  • To develop and analyze a modified Sparse Distributed Memory (SDM) system utilizing spiking neurons.
  • To investigate the storage efficiency and scalability of this novel neural network architecture.

Main Methods:

  • The proposed model employs sparse binary N-of-M codes and unipolar binary synaptic weights.
  • A two-layer network architecture is used, combining an address decoder with a correlation matrix memory.
  • A simple Hebbian learning rule facilitates memory storage and retrieval.

Related Experiment Videos

Main Results:

  • The spiking neural network-based SDM demonstrates good storage efficiency.
  • The network architecture is shown to be scalable for larger memory capacities.
  • Numerical simulations validate performance in both noiseless and noisy environments.

Conclusions:

  • The modified SDM provides a viable and efficient approach for implementing associative memory using spiking neurons.
  • The findings enable optimized configuration of the memory system for diverse operational conditions.
  • This research contributes to the development of advanced neural network memory systems.