Understanding the Functional Roles of Modelling Components in Spiking Neural Networks
This work provides insights for optimizing SNNs in neuromorphic computing, though it is incremental as it systematically analyzes existing components rather than introducing new methods.
The authors investigated the functional roles of leakage, reset, and recurrence components in leaky integrate-and-fire spiking neural networks to address optimization challenges, finding that leakage balances memory and robustness, reset aids temporal processing and efficiency, and recurrence enhances dynamics but reduces robustness.
Spiking neural networks (SNNs), inspired by the neural circuits of the brain, are promising in achieving high computational efficiency with biological fidelity. Nevertheless, it is quite difficult to optimize SNNs because the functional roles of their modelling components remain unclear. By designing and evaluating several variants of the classic model, we systematically investigate the functional roles of key modelling components, leakage, reset, and recurrence, in leaky integrate-and-fire (LIF) based SNNs. Through extensive experiments, we demonstrate how these components influence the accuracy, generalization, and robustness of SNNs. Specifically, we find that the leakage plays a crucial role in balancing memory retention and robustness, the reset mechanism is essential for uninterrupted temporal processing and computational efficiency, and the recurrence enriches the capability to model complex dynamics at a cost of robustness degradation. With these interesting observations, we provide optimization suggestions for enhancing the performance of SNNs in different scenarios. This work deepens the understanding of how SNNs work, which offers valuable guidance for the development of more effective and robust neuromorphic models.