EUVIMEDEUVIMED entdecken
Crossref

Improving Recall in Sparse Associative Memories That Use Neurogenesis

Katy Warr, Jonathon Hare, David Thomas

Neural Computation · 2025

DOI: 10.1162/neco_a_01732 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Computation, 2025. Verfasst von Katy Warr und 2 weiteren Autor:innen. Beteiligte Einrichtung: Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, U.K. k.s.warr@soton.ac.uk. Hauptthemen laut MEDLINE: Neurogenesis, Mental Recall, Neural Networks, Computer, Models, Neurological. Die Arbeit nennt 30 Literaturangaben. Gefördert von: U.K. Research and Innovation Engineering and Physical Sciences Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The creation of future low-power neuromorphic solutions requires specialist spiking neural network (SNN) algorithms that are optimized for neuromorphic settings. One such algorithmic challenge is the ability to recall learned patterns from their noisy variants. Solutions to this problem may be required to memorize vast numbers of patterns based on limited training data and subsequently recall the patterns in the presence of noise. To solve this problem, previous work has explored sparse associative memory (SAM)—associative memory neural models that exploit the principle of sparse neural coding observed in the brain. Research into a subcategory of SAM has been inspired by the biological process of adult neurogenesis, whereby new neurons are generated to facilitate adaptive and effective lifelong learning. Although these neurogenesis models have been demonstrated in previous research, they have limitations in terms of recall memory capacity and robustness to noise. In this article, we provide a unifying framework for characterizing a type of SAM network that has been pretrained using a learning strategy that incorporated a simple neurogenesis model. Using this characterization, we formally define network topology and threshold optimization methods to empirically demonstrate greater than 104 times improvement in memory capacity compared to previous work. We show that these optimizations can facilitate the development of networks that have reduced interneuron connectivity while maintaining high recall efficacy. This paves the way for ongoing research into fast, effective, low-power realizations of associative memory on neuromorphic platforms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeurogenesisMental RecallNeural Networks, ComputerModels, NeurologicalAssociation LearningMemoryHumansNeuronsAlgorithmsAnimals

Autor:innen und Institutionen

  • Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, U.K. k.s.warr@soton.ac.uk.
  • Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, U.K. j.s.hare@soton.ac.uk.
  • Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, U.K. d.b.thomas@soton.ac.uk.

Förderung

  • U.K. Research and Innovation Engineering and Physical Sciences Research Council

Zitieren

APA

Warr, K., Hare, J., & Thomas, D. (2025). Improving Recall in Sparse Associative Memories That Use Neurogenesis. Neural Computation. https://doi.org/10.1162/neco_a_01732

Vancouver

Warr K, Hare J, Thomas D. Improving Recall in Sparse Associative Memories That Use Neurogenesis. Neural Computation. 2025. doi:10.1162/neco_a_01732

BibTeX
@article{Warr2025,
  author = {Warr, Katy and Hare, Jonathon and Thomas, David},
  title = {Improving Recall in Sparse Associative Memories That Use Neurogenesis},
  journal = {Neural Computation},
  year = {2025},
  doi = {10.1162/neco_a_01732}
}
Kostenlos starten →