PreprintarXiv licencearXiv
Neural Learning as a Game Induced by Spike-Timing-Dependent Plasticity
Abstract
A general framework for inferring the computational role of spike-timing-dependent plasticity (STDP) does not currently exist. Here, we develop a game-theoretic description for a canonical, convergent neural circuit with general STDP and postsynaptic-potential (PSP) kernels. Parity-matched STDP-PSP interactions induce a potential game among presynaptic neurons, whereas parity-mismatched interactions induce a zero-sum game. These components, respectively, implement contrastive PCA and flow selection; their weighted interplay determines learning dynamics and computation for arbitrary STDP rules.
Related
- Bio-inspired minimal hardware implementation of spike-time dependent plasticity for intelligent spiking neural networks
- Learning Memory-Dependent Neural Network Correlation Potentials for Accurate Electron Dynamics
- Learning-Induced Dynamical Transition in Recurrent Neural Networks
- When do machine-learning potentials need a configuration-dependent kernel? Learning long-range interactions with Fourier neural operators
- Self-compensation method for atmospheric refraction-induced deviations in satellite-to-ground one-way laser timing and positioning
BibTeX
@misc{fan2026neural,
title = {{Neural Learning as a Game Induced by Spike-Timing-Dependent Plasticity}},
author = {Xinhao Fan and Shreesh P. Mysore},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21131},
eprint = {2609.21131},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21131},
}
RIS
TY - UNPB
TI - Neural Learning as a Game Induced by Spike-Timing-Dependent Plasticity
AU - Xinhao Fan
AU - Shreesh P. Mysore
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.21131
UR - https://arxiv.org/abs/2609.21131
AB - A general framework for inferring the computational role of spike-timing-dependent plasticity (STDP) does not currently exist. Here, we develop a game-theoretic description for a canonical, convergent neural circuit with general STDP and postsynaptic-potential (PSP) kernels. Parity-matched STDP-PSP interactions induce a potential game among presynaptic neurons, whereas parity-mismatched interactions induce a zero-sum game. These components, respectively, implement contrastive PCA and flow selection; their weighted interplay determines learning dynamics and computation for arbitrary STDP rules.
ER -