arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2509.06970q-bio.NCcs.AI
收藏

神经元模型对脉冲神经网络性能的影响:一种基于复杂度的分类方法

Impact of Neuron Models on Spiking Neural Networks performance. A Complexity Based Classification Approach

Institute of Fundamental Technological Research, Polish Academy of Sciences(波兰科学院基础技术研究所)

Zofia Rudnicka, Janusz Szczepanski, Agnieszka Pregowska

AI总结:

本研究通过基于Lempel-Ziv复杂度的评估方法,系统比较了多种神经元模型和学习规则对脉冲神经网络分类性能的影响,发现分类精度取决于模型、网络规模和学习规则的相互作用。

摘要:

本研究探讨了神经元模型和学习规则的选择如何影响脉冲神经网络(SNN)的分类性能,重点关注生物信号处理中的应用。我们比较了多种生物启发的神经元模型,包括漏积分发放(LIF)模型、元神经元和概率性Levy-Baxter(LB)神经元,并跨多种学习规则进行评估,包括脉冲时序依赖可塑性(STDP)、tempotron和奖励调制更新。本工作的一个新颖之处在于将基于复杂度的决策机制整合到评估流程中。利用Lempel-Ziv复杂度(LZC),一种与熵率相关的度量,我们量化了脉冲序列的结构规律性,并以一致且可解释的方式评估不同SNN配置下的分类结果。为了研究神经动力学并评估算法性能,我们使用了具有不同时间依赖性和随机性水平的合成数据集,包括马尔可夫过程和泊松过程,这些是模拟神经元脉冲序列并捕捉生物神经元随机发放行为的成熟模型。对合成泊松和马尔可夫模型数据的验证揭示了清晰的性能趋势:分类精度取决于神经元模型、网络规模和学习规则之间的相互作用,基于LZC的评估突出了对弱信号或噪声信号保持鲁棒的配置。这项工作系统地分析了神经元模型选择如何与网络参数和学习策略相互作用,并得到一种新颖的基于复杂度的评估方法的支持,该方法为SNN性能提供了一致的基准。

英文摘要:

This study explores how the selection of neuron models and learning rules impacts the classification performance of Spiking Neural Networks (SNNs), with a focus on applications in bio-signal processing. We compare biologically inspired neuron models, including Leaky Integrate-and-Fire (LIF), metaneurons, and probabilistic Levy-Baxter (LB) neurons, across multiple learning rules, including spike-timing-dependent plasticity (STDP), tempotron, and reward-modulated updates. A novel element of this work is the integration of a complexity-based decision mechanism into the evaluation pipeline. Using Lempel-Ziv Complexity (LZC), a measure related to entropy rate, we quantify the structural regularity of spike trains and assess classification outcomes in a consistent and interpretable manner across different SNN configurations. To investigate neural dynamics and assess algorithm performance, we employed synthetic datasets with varying temporal dependencies and stochasticity levels. These included Markov and Poisson processes, well-established models to simulate neuronal spike trains and capture the stochastic firing behavior of biological neurons.Validation of synthetic Poisson and Markov-modeled data reveals clear performance trends: classification accuracy depends on the interaction between neuron model, network size, and learning rule, with the LZC-based evaluation highlighting configurations that remain robust to weak or noisy signals. This work delivers a systematic analysis of how neuron model selection interacts with network parameters and learning strategies, supported by a novel complexity-based evaluation approach that offers a consistent benchmark for SNN performance.

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。

↑