Role of short-term plasticity and slow temporal dynamics in enhancing time series prediction with a brain-inspired recurrent neural network
Chaos: An Interdisciplinary Journal of Nonlinear Science · 2025
DOI: 10.1063/5.0233158 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, 2025. Verfasst von Artem Pilzak und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Psychology, University of Ottawa, 156 Jean-Jacques Lussier, Ottawa, Ontario K1N 6N5, Canada. Hauptthemen laut MEDLINE: Neuronal Plasticity, Neural Networks, Computer, Brain, Models, Neurological. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Typical reservoir networks are based on random connectivity patterns that differ from brain circuits in two important ways. First, traditional reservoir networks lack synaptic plasticity among recurrent units, whereas cortical networks exhibit plasticity across all neuronal types and cortical layers. Second, reservoir networks utilize random Gaussian connectivity, while cortical networks feature a heavy-tailed distribution of synaptic strengths. It is unclear what are the computational advantages of these features for predicting complex time series. In this study, we integrated short-term plasticity (STP) and lognormal connectivity into a novel recurrent neural network (RNN) framework. The model exhibited rich patterns of population activity characterized by slow coordinated fluctuations. Using graph spectral decomposition, we show that weighted networks with lognormal connectivity and STP yield higher complexity than several graph types. When tested on various tasks involving the prediction of complex time series data, the RNN model outperformed a baseline model with random connectivity as well as several other network architectures. Overall, our results underscore the potential of incorporating brain-inspired features such as STP and heavy-tailed connectivity to enhance the robustness and performance of artificial neural networks in complex data prediction and signal processing tasks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Psychology, University of Ottawa, 156 Jean-Jacques Lussier, Ottawa, Ontario K1N 6N5, Canada.
- Brain and Mind Research Institute, University of Ottawa, 451 Smyth Rd., Ottawa, Ontario K1H 8M5, Canada.
ORCID-Profile: Artem Pilzak, Nareg Berberian, Jean-Philippe Thivierge
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Pilzak, A., Calderini, M., Berberian, N., & Thivierge, J. P. (2025). Role of short-term plasticity and slow temporal dynamics in enhancing time series prediction with a brain-inspired recurrent neural network. Chaos: An Interdisciplinary Journal of Nonlinear Science. https://doi.org/10.1063/5.0233158
Vancouver
Pilzak A, Calderini M, Berberian N, Thivierge JP. Role of short-term plasticity and slow temporal dynamics in enhancing time series prediction with a brain-inspired recurrent neural network. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2025. doi:10.1063/5.0233158
BibTeX
@article{Pilzak2025,
author = {Pilzak, Artem and Calderini, Matias and Berberian, Nareg and Thivierge, Jean-Philippe},
title = {Role of short-term plasticity and slow temporal dynamics in enhancing time series prediction with a brain-inspired recurrent neural network},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2025},
doi = {10.1063/5.0233158}
}
EUVIMED