EUVIMEDEUVIMED entdecken
Crossref

Toward a Biologically Plausible SNN-Based Associative Memory with Context-Dependent Hebbian Connectivity

S Yu Makovkin iD, S Yu Gordleeva iD, I A Kastalskiy iD

International Journal of Neural Systems · 2025

DOI: 10.1142/s0129065725500273 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, 2025. Verfasst von S Yu Makovkin und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Mathematics, Institute of Information Technology, Mathematics and Mechanics, Lobachevsky State University of Nizhny Novgorod, 2…. Hauptthemen laut MEDLINE: Neural Networks, Computer, Memory, Models, Neurological, Neurons. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Russian Science Foundation, Ministry of Science and Higher Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose a spiking neural network model with Hebbian connectivity for implementing energy-efficient associative memory, whose activity is determined by input stimuli. The model consists of three interacting layers of Hodgkin–Huxley–Mainen spiking neurons with excitatory and inhibitory synaptic connections. Information patterns are stored in memory using a symmetric Hebbian matrix and can be retrieved in response to a specific stimulus pattern. Binary images are encoded using in-phase and anti-phase oscillations relative to a global clock signal. Utilizing the phase-locking effect allows for cluster synchronization of neurons (both on the input and output layers). Interneurons in the intermediate layer filter signal propagation pathways depending on the context of the input layer, effectively engaging only a portion of the synaptic connections within the Hebbian matrix for recognition. The stability of the oscillation phase is investigated for both in-phase and anti-phase synchronization modes when recognizing direct and inverse images. This context-dependent effect opens promising avenues for the development of analog hardware circuits for energy-efficient neurocomputing applications, potentially leading to breakthroughs in artificial intelligence and cognitive computing.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerMemoryModels, NeurologicalNeuronsAssociation LearningHumansAction PotentialsSynapses

Stichwörter der Autor:innen

Hebbian connectivityHodgkin–Huxley–Mainen neuronSpiking neural networkpattern retrievalphase locking

Autor:innen und Institutionen

  • Department of Applied Mathematics, Institute of Information Technology, Mathematics and Mechanics, Lobachevsky State University of Nizhny Novgorod, 23 Gagarin Avenue, Nizhny Novgorod 603022, Russia.
  • Neuromorphic Computing Center, Neimark University, 6 Nartova Street, Nizhny Novgorod 603081, Russia.
  • Baltic Center for Neurotechnology and Artificial Intelligence, Immanuel Kant Baltic Federal University, 14 A. Nevskogo Street, Kaliningrad 236041, Russia.
  • Scientific and Educational Mathematical Center "Mathematics of Future Technologies", Lobachevsky State University of Nizhny Novgorod, 23 Gagarin Avenue, Nizhny Novgorod 603022, Russia.
  • Department of Neurotechnology, Institute of Biology and Biomedicine, Lobachevsky State University of Nizhny Novgorod, 23 Gagarin Avenue, Nizhny Novgorod 603022, Russia.
  • Laboratory of Neurobiomorphic Technologies, Moscow Institute of Physics and Technology, 9 Institutskiy Lane, Dolgoprudny 141701, Moscow Region, Russia.

ORCID-Profile: S Yu Makovkin, S Yu Gordleeva, I A Kastalskiy

Förderung

  • Russian Science Foundation
  • Ministry of Science and Higher Education

Zitieren

APA

Makovkin, S. Y., Gordleeva, S. Y., & Kastalskiy, I. A. (2025). Toward a Biologically Plausible SNN-Based Associative Memory with Context-Dependent Hebbian Connectivity. International Journal of Neural Systems. https://doi.org/10.1142/s0129065725500273

Vancouver

Makovkin SY, Gordleeva SY, Kastalskiy IA. Toward a Biologically Plausible SNN-Based Associative Memory with Context-Dependent Hebbian Connectivity. International Journal of Neural Systems. 2025. doi:10.1142/s0129065725500273

BibTeX
@article{Makovkin2025,
  author = {Makovkin, S Yu and Gordleeva, S Yu and Kastalskiy, I A},
  title = {Toward a Biologically Plausible SNN-Based Associative Memory with Context-Dependent Hebbian Connectivity},
  journal = {International Journal of Neural Systems},
  year = {2025},
  doi = {10.1142/s0129065725500273}
}
Kostenlos starten →