Plasticity Dynamics Improves Reservoir Performance on Mixed-Timescale Memory Tasks
- 1Georg-August University
Abstract
Mixed-timescale signals are ubiquitous in natural stimuli and real-world applications, yet they remain challenging to process with recurrent neural networks. Reservoir computing offers an efficient framework for temporal processing, but extending its temporal range typically requires tuning neuronal timescales, which can compromise the representation of faster dynamics. Here, we propose an alternative approach in which synaptic plasticity provides an additional, slower timescale for computation. We introduce Hebbian plasticity into recurrent networks and show that its dynamics enable the reservoir to simultaneously process fast and slow components of mixed-timescale inputs: neuronal dynamics encode fast fluctuations, while synaptic dynamics support slower components. Remarkably, the resulting computational benefit extends over more than an order of magnitude beyond the intrinsic timescale of the plasticity. We show that this extended processing range arises from the dependence of the plasticity rule on postsynaptic activity, which effectively injects a filtered memory of past states into the network current. These results identify synaptic plasticity as a mechanism for extending the temporal processing capabilities of recurrent networks without altering neuronal timescales, and also suggest a potential computational role for plastic synapses in the processing of slowly varying stimuli in biological neuronal networks.
Related
- Learning to play with spikes: characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing
- Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
- Long-timescale dynamics shape visual conscious awareness
- Recording proteome dynamics in the late-stage embryo at hour-timescale, spatial, and single-cell resolution with MEMBRYO
- High-fat diet consumption increases hippocampal plasticity and affects performance in a spatial learning task in young female mice
BibTeX
@misc{becker2026plasticity,
title = {{Plasticity Dynamics Improves Reservoir Performance on Mixed-Timescale Memory Tasks}},
author = {M. P. Becker and M. Fauth},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.754073},
url = {https://www.biorxiv.org/content/10.64898/2026.09.24.754073v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Plasticity Dynamics Improves Reservoir Performance on Mixed-Timescale Memory Tasks
AU - M. P. Becker
AU - M. Fauth
PY - 2026
DA - 2026/09/24
PB - bioRxiv
DO - 10.64898/2026.09.24.754073
UR - https://www.biorxiv.org/content/10.64898/2026.09.24.754073v1
AB - Mixed-timescale signals are ubiquitous in natural stimuli and real-world applications, yet they remain challenging to process with recurrent neural networks. Reservoir computing offers an efficient framework for temporal processing, but extending its temporal range typically requires tuning neuronal timescales, which can compromise the representation of faster dynamics. Here, we propose an alternative approach in which synaptic plasticity provides an additional, slower timescale for computation. We introduce Hebbian plasticity into recurrent networks and show that its dynamics enable the reservoir to simultaneously process fast and slow components of mixed-timescale inputs: neuronal dynamics encode fast fluctuations, while synaptic dynamics support slower components. Remarkably, the resulting computational benefit extends over more than an order of magnitude beyond the intrinsic timescale of the plasticity. We show that this extended processing range arises from the dependence of the plasticity rule on postsynaptic activity, which effectively injects a filtered memory of past states into the network current. These results identify synaptic plasticity as a mechanism for extending the temporal processing capabilities of recurrent networks without altering neuronal timescales, and also suggest a potential computational role for plastic synapses in the processing of slowly varying stimuli in biological neuronal networks.
ER -