Learning to play with spikes: characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing
- 1Institute of Science and Technology Austria
Abstract
Spiking reservoir computing, and reservoir computing more generally, is a powerful and efficient framework for neuromorphic and biological applications, in which a fixed random reservoir drives a trained readout. Its performance depends critically on the reservoir initialization, so that enriching the reservoir with adaptive, unsupervised plasticity rules offers a natural solution to this limitation. However, it is unclear which rules work, or why, and how to find the best-suited rules for specific tasks without exhaustive and expensive search. Here, we learn how to play the Atari game Pong in a plastic spiking reservoir network. We systematically characterize a large family of local plasticity rules that were meta-learned in prior work. We then show that their performance is predictable and structured: high-scoring rules are characterized by strong differentiation between neurons encoding the ball trajectory and the background, with stable weight dynamics, and consistent readout alignment across time. These mechanistic signatures are not task-specific and transfer to a delayed-match recognition task. Rule performance can be estimated from rule parameters alone. Finally, conditioning simulation-based inference (SBI) on high scores allows us to sample directly from promising regions of the rule space, to discover rules that exceed the performance of those found in the prior distribution and reveal stable, high-performing configurations. Together, these results offer competitive performance against classical reservoir computing while providing a transparent, interpretable account of what makes a plasticity rule useful for neuromorphic hardware and biological computing.
Related
- Plasticity Dynamics Improves Reservoir Performance on Mixed-Timescale Memory Tasks
- Simple but effective unsupervised classification for specified domain images: a case study on fungi images
- Unsupervised 3D classification and characterisation of osteocyte and chondrocyte lacunae in the murine osteochondral unit
- Multi-scale microenvironment covariance for unsupervised spatial domain identification
- Unsupervised neuronal cell typing from connectivity by minimum description length
BibTeX
@misc{kania2026learning,
title = {{Learning to play with spikes: characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing}},
author = {M. Kania and B. Confavreux and T. P. Vogels},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.15.751573},
url = {https://www.biorxiv.org/content/10.64898/2026.09.15.751573v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Learning to play with spikes: characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing
AU - M. Kania
AU - B. Confavreux
AU - T. P. Vogels
PY - 2026
DA - 2026/09/15
PB - bioRxiv
DO - 10.64898/2026.09.15.751573
UR - https://www.biorxiv.org/content/10.64898/2026.09.15.751573v1
AB - Spiking reservoir computing, and reservoir computing more generally, is a powerful and efficient framework for neuromorphic and biological applications, in which a fixed random reservoir drives a trained readout. Its performance depends critically on the reservoir initialization, so that enriching the reservoir with adaptive, unsupervised plasticity rules offers a natural solution to this limitation. However, it is unclear which rules work, or why, and how to find the best-suited rules for specific tasks without exhaustive and expensive search. Here, we learn how to play the Atari game Pong in a plastic spiking reservoir network. We systematically characterize a large family of local plasticity rules that were meta-learned in prior work. We then show that their performance is predictable and structured: high-scoring rules are characterized by strong differentiation between neurons encoding the ball trajectory and the background, with stable weight dynamics, and consistent readout alignment across time. These mechanistic signatures are not task-specific and transfer to a delayed-match recognition task. Rule performance can be estimated from rule parameters alone. Finally, conditioning simulation-based inference (SBI) on high scores allows us to sample directly from promising regions of the rule space, to discover rules that exceed the performance of those found in the prior distribution and reveal stable, high-performing configurations. Together, these results offer competitive performance against classical reservoir computing while providing a transparent, interpretable account of what makes a plasticity rule useful for neuromorphic hardware and biological computing.
ER -