Delays in Spiking Neural Networks: A State Space Model Approach

2025/12/01 by Sanja Karilanova, Karilanova, Sanja, Subhrakanti Dey +3 · 1 citation
Computer Science · Engineering · #Advanced Memory and Neural Computing #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Machine Learning (cs.LG) #Neural Networks and Reservoir Computing

paper · pdf · doi:10.48550/arxiv.2512.01906

openalex publication_date 2025/12/01 · openalex created_date 2025/12/03 · openalex updated_date 2026/07/28

Abstract

Spiking neural networks (SNNs) are biologically inspired, event-driven models suited for temporal data processing and energy-efficient neuromorphic computing. In SNNs, richer neuronal dynamic allows capturing more complex temporal dependencies, with delays playing a crucial role by allowing past inputs to directly influence present spiking behavior. We propose a general framework for incorporating delays into SNNs through additional state variables. The proposed mechanism enables each neuron to access a finite temporal input history. The framework is agnostic to neuron models and hence can be seamlessly integrated into standard spiking neuron models such as Leaky Integrate-and-Fire (LIF) and Adaptive LIF (adLIF). We analyze how the duration of the delays and the learnable parameters associated with them affect the performance. We investigate the trade-offs in the network architecture due to additional state variables introduced by the delay mechanism. Experiments on the Spiking Heidelberg Digits (SHD) dataset show that the proposed mechanism matches existing delay-based SNNs in performance while remaining computationally efficient, with particular gains in smaller networks.

Citations

• Algorithm-hardware co-design of neuromorphic networks with dual memory pathways
• Exploiting heterogeneous delays for efficient computation in low-bit neural networks
• DelRec: learning delays in recurrent spiking neural networks
• Low-Bit Data Processing Using Multiple-Output Spiking Neurons with Non-linear Reset Feedback
• Extending Spike-Timing Dependent Plasticity to Learning Synaptic Delays
• State-Space Model Inspired Multiple-Input Multiple-Output Spiking Neurons
• Efficient Synaptic Delay Implementation in Digital Event-Driven AI Accelerators
• Efficient Event-based Delay Learning in Spiking Neural Networks
• Zero-Shot Temporal Resolution Domain Adaptation for Spiking Neural Networks
• The Role of Temporal Hierarchy in Spiking Neural Networks
• Accurate Mapping of RNNs on Neuromorphic Hardware with Adaptive Spiking Neurons
• Learning Delays Through Gradients and Structure: Emergence of Spatiotemporal Patterns in Spiking Neural Networks
• DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardware
• Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models
• DenRAM: Neuromorphic Dendritic Architecture with RRAM for Efficient Temporal Processing with Delays
• Co-learning synaptic delays, weights and adaptation in spiking neural networks
• Spiking Structured State Space Model for Monaural Speech Enhancement
• Effectively Modeling Time Series with Simple Discrete State Spaces
• Hungry Hungry Hippos: Towards Language Modeling with State Space Models
• Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic Hardware
• Diagonal State Spaces are as Effective as Structured State Spaces
• Efficiently Modeling Long Sequences with Structured State Spaces
• Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook
• Surrogate Gradient Learning in Spiking Neural Networks
• SLAYER: Spike Layer Error Reassignment in Time
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• A circuit for detection of interaural time differences in the brain stem of the barn owl
• Networks of spiking neurons: The third generation of neural network models

Cited by

• Algorithm-hardware co-design of neuromorphic networks with dual memory pathways

Related

• Efficient Event-based Delay Learning in Spiking Neural Networks
• Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects
• DelRec: learning delays in recurrent spiking neural networks
• Learning Delays Through Gradients and Structure: Emergence of Spatiotemporal Patterns in Spiking Neural Networks
• Bio-plausible Unsupervised Delay Learning for Extracting Temporal Features in Spiking Neural Networks