Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamics
This work addresses a fundamental limitation in SNN models for researchers and practitioners in neuromorphic computing, offering improved robustness and efficiency, though it is incremental as it builds on existing LIF neurons.
The paper tackled the problem of spiking neural networks (SNNs) overlooking the refractory period of biological neurons by proposing RPLIF, a method that incorporates spike-triggered threshold dynamics into LIF neurons, achieving state-of-the-art performance on neuromorphic datasets like Cifar10-DVS (82.40%) and N-Caltech101 (83.35%) with fewer timesteps.
As the third generation of neural networks, spiking neural networks (SNNs) have recently gained widespread attention for their biological plausibility, energy efficiency, and effectiveness in processing neuromorphic datasets. To better emulate biological neurons, various models such as Integrate-and-Fire (IF) and Leaky Integrate-and-Fire (LIF) have been widely adopted in SNNs. However, these neuron models overlook the refractory period, a fundamental characteristic of biological neurons. Research on excitable neurons reveal that after firing, neurons enter a refractory period during which they are temporarily unresponsive to subsequent stimuli. This mechanism is critical for preventing over-excitation and mitigating interference from aberrant signals. Therefore, we propose a simple yet effective method to incorporate the refractory period into spiking LIF neurons through spike-triggered threshold dynamics, termed RPLIF. Our method ensures that each spike accurately encodes neural information, effectively preventing neuron over-excitation under continuous inputs and interference from anomalous inputs. Incorporating the refractory period into LIF neurons is seamless and computationally efficient, enhancing robustness and efficiency while yielding better performance with negligible overhead. To the best of our knowledge, RPLIF achieves state-of-the-art performance on Cifar10-DVS(82.40%) and N-Caltech101(83.35%) with fewer timesteps and demonstrates superior performance on DVS128 Gesture(97.22%) at low latency.