用复杂度指标分析脉冲网络学习规则的精度与效率权衡
Accuracy-Efficiency Trade-Offs in Spiking Neural Networks: A Lempel-Ziv Complexity Perspective on Learning Rules
- 用莱普尔-兹伊夫复杂度量化脉冲序列时间结构变化
- 梯度法精度最高但计算开销大，生物启发规则更高效
- 适合关注能效比的神经形态计算应用者参考
训练脉冲神经网络（SNN）因时间动态性、脉冲事件不可微以及稀疏激活而困难。本文研究不同学习范式（无监督、有监督、混合）在时序模式识别中对分类性能和计算成本的影响。基于前期工作，采用莱普尔-兹伊夫复杂度（LZC）作为紧凑且决策相关的脉冲序列时间组织描述符，量化不同学习规则如何重塑类条件时间结构。该方法结合漏电积分-发放（LIF）SNN与基于LZC的判别规则，在具有可控时序统计的合成数据（伯努利、两状态马尔可夫、泊松脉冲过程）及两个类别子集的MNIST和N-MNIST上评估学习规则。结果表明：梯度法在所有数据集上实现最高准确率但计算成本高；而生物启发规则（如Tempotron和SpikeProp）提供更优的精度-效率平衡。研究强调学习规则的选择应根据应用场景约束及期望的可分性与计算开销之间的权衡。
原文摘要 · Abstract (English)
Training spiking neural networks (SNNs) remains challenging due to temporal dynamics, non-differentiability of spike events, and sparse event-driven activations. This paper studies how the choice of learning paradigm (unsupervised, supervised, and hybrid) affects classification performance and computational cost in temporal pattern recognition. Building on our earlier study [Rudnicka et al., 2026], we use Lempel-Ziv complexity (LZC) as a compact, decision-relevant descriptor of spike-train temporal organization to quantify how different learning rules reshape class-conditional temporal structure. The pipeline combines a leaky integrate-and-fire (LIF) SNN with an LZC-based decision rule. We evaluate learning rules on synthetic sources with controlled temporal statistics (Bernoulli, two-state Markov, and Poisson spike processes) and on two-class subsets of MNIST and N-MNIST. Across datasets, gradient-based learning achieves the highest accuracy but at high computational cost, whereas bio-inspired rules (e.g., Tempotron and SpikeProp) offer favorable accuracy--efficiency trade-offs. These results highlight that selecting a learning rule should be guided by application constraints and the desired balance between separability and computational overhead.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。