ChronoPlastic Spiking Neural Networks

TL;DR

This paper introduces ChronoPlastic Spiking Neural Networks (CPSNNs), which dynamically adapt synaptic decay rates to improve learning of long-range temporal dependencies in a biologically plausible and efficient manner.

Contribution

CPSNNs embed adaptive temporal control within local synaptic dynamics, enabling faster and more reliable learning of long-term dependencies compared to prior methods.

Findings

CPSNNs learn long-gap dependencies faster than standard SNNs.

CPSNNs maintain linear-time complexity and neuromorphic compatibility.

Empirical results show improved reliability in temporal learning.

Abstract

Spiking neural networks (SNNs) offer a biologically grounded and energy-efficient alternative to conventional neural architectures; however, they struggle with long-range temporal dependencies due to fixed synaptic and membrane time constants. This paper introduces ChronoPlastic Spiking Neural Networks (CPSNNs), a novel architectural principle that enables adaptive temporal credit assignment by dynamically modulating synaptic decay rates conditioned on the state of the network. CPSNNs maintain multiple internal temporal traces and learn a continuous time-warping function that selectively preserves task-relevant information while rapidly forgetting noise. Unlike prior approaches based on adaptive membrane constants, attention mechanisms, or external memory, CPSNNs embed temporal control directly within local synaptic dynamics, preserving linear-time complexity and neuromorphic compatibility. We provide a formal description of the model, analyze its computational properties, and demonstrate empirically that CPSNNs learn long-gap temporal dependencies significantly faster and more reliably than standard SNN baselines. Our results suggest that adaptive temporal modulation is a key missing ingredient for scalable temporal learning in spiking systems.