ChronoPlastic Spiking Neural Networks
This addresses a key bottleneck for scalable temporal learning in energy-efficient spiking neural networks, offering a novel architectural principle with potential neuromorphic applications.
The paper tackles the problem of spiking neural networks struggling with long-range temporal dependencies by introducing ChronoPlastic Spiking Neural Networks (CPSNNs), which enable adaptive temporal credit assignment through dynamic modulation of synaptic decay rates, resulting in significantly faster and more reliable learning of long-gap dependencies compared to standard SNN baselines.
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.