面向神经形态视觉的节能脉冲预算持续学习
Energy-Aware Spike Budgeting for Continual Learning in Spiking Neural Networks for Neuromorphic Vision
AI总结：
提出一种面向神经形态视觉的节能脉冲预算持续学习框架，通过整合经验回放、可学习神经元参数和自适应调度器，在帧型和事件型数据集上分别提升准确率并降低能耗。
摘要：
基于脉冲神经网络（SNNs）的神经形态视觉系统为事件型和帧型相机提供了超低功耗感知能力，但灾难性遗忘仍是持续演进环境中部署的关键障碍。现有持续学习方法主要针对人工神经网络，很少同时优化准确率和能耗效率，尤其在事件型数据集上的探索有限。我们提出了一种面向持续学习的SNN节能脉冲预算框架，整合了经验回放、可学习的泄漏积分-放电神经元参数以及自适应脉冲调度器，在训练过程中强制执行数据集特定的能耗约束。我们的方法表现出模态依赖性：在帧型数据集（MNIST、CIFAR-10）上，脉冲预算管理作为稀疏性诱导正则化器，提高准确率的同时将脉冲率降低高达47%；在事件型数据集（DVS-Gesture、N-MNIST、CIFAR-10-DVS）上，受控预算放松使准确率提升高达17.45个百分点，且计算开销极低。在涵盖两种模态的五个基准测试中，我们的方法在最小化动态功耗的同时展现出一致的性能提升，推动了神经形态视觉系统持续学习的实用可行性。
英文摘要：
Neuromorphic vision systems based on spiking neural networks (SNNs) offer ultra-low-power perception for event-based and frame-based cameras, yet catastrophic forgetting remains a critical barrier to deployment in continually evolving environments. Existing continual learning methods, developed primarily for artificial neural networks, seldom jointly optimize accuracy and energy efficiency, with particularly limited exploration on event-based datasets. We propose an energy-aware spike budgeting framework for continual SNN learning that integrates experience replay, learnable leaky integrate-and-fire neuron parameters, and an adaptive spike scheduler to enforce dataset-specific energy constraints during training. Our approach exhibits modality-dependent behavior: on frame-based datasets (MNIST, CIFAR-10), spike budgeting acts as a sparsity-inducing regularizer, improving accuracy while reducing spike rates by up to 47\%; on event-based datasets (DVS-Gesture, N-MNIST, CIFAR-10-DVS), controlled budget relaxation enables accuracy gains up to 17.45 percentage points with minimal computational overhead. Across five benchmarks spanning both modalities, our method demonstrates consistent performance improvements while minimizing dynamic power consumption, advancing the practical viability of continual learning in neuromorphic vision systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
