异质性增强的随机共振改善延迟脉冲神经网络中的液态计算
Heterogeneity-enhanced stochastic resonance improves liquid-state computing in delayed spiking neural networks
浏览论文内容
中文总结 AI 辅助
本研究揭示随机强迫与结构异质性协同调控随机共振，可提升延迟脉冲神经网络中液态状态机的预测性能，且增强效果取决于无序分布类型而非仅幅度。
中文摘要 AI 辅助
我们研究了随机强迫和淬火结构异质性对可激发FitzHugh--Nagumo神经元小世界网络中随机共振（SR）和液态计算的联合效应。异质性分别通过耦合强度和时间延迟引入，这些耦合强度和时间延迟从高斯分布、双峰分布和移位指数分布中抽取。弱周期强迫解析了随机共振景观，而弱非周期驱动则探测了噪声辅助的信号编码和液态状态机（LSM）预测。异质性并非普遍有益，而是以依赖于分布的方式重组共振景观和计算性能。高斯耦合无序拓宽了强响应区域，而双峰无序产生了更显著的增强，并将共振移向较弱噪声。移位指数耦合无序的行为不同：增加其尺度会拓宽耦合分布并将其移向响应较弱的区域。时间延迟异质性可以增强或抑制SR，具体取决于延迟分布如何采样结构化的延迟-响应景观。在非周期强迫下，更强的输入-输出相干性与较低的LSM预测误差相伴，表明SR可以改善LSM性能，且适当的耦合异质性可以进一步增强这种计算益处；高斯和双峰耦合无序将最优值移向较弱噪声，并降低了噪声优化的均方根预测误差，其中双峰情况获得了最大降低。这些结果将随机强迫和淬火异质性识别为耦合控制参数，并表明LSM的计算增强取决于无序结构而非仅取决于幅度。
英文摘要
We investigate the joint effects of stochastic forcing and quenched structural heterogeneity on stochastic resonance (SR) and liquid-state computation in a small-world network of excitable FitzHugh--Nagumo neurons. Heterogeneity is introduced separately through coupling strengths and time delays drawn from Gaussian, bimodal, and shifted-exponential distributions. Weak periodic forcing resolves the stochastic-resonance landscape, whereas weak aperiodic driving probes noise-assisted signal encoding and Liquid State Machine (LSM) forecasting. Heterogeneity is not generically beneficial, but reorganizes the resonance landscape and computational performance in a distribution-dependent manner. Gaussian coupling disorder broadens the strong-response region, whereas bimodal disorder produces a more pronounced enhancement and shifts resonance toward weaker noise. Shifted-exponential coupling disorder behaves differently: increasing its scale broadens and shifts the coupling distribution toward less responsive regions. Time-delay heterogeneity can enhance or suppress SR depending on how the delay distribution samples the structured delay-response landscape. Under aperiodic forcing, stronger input--output coherence accompanies lower LSM prediction error, showing that SR can improve LSM performance and that suitable coupling heterogeneity can further enhance this computational benefit; Gaussian and bimodal coupling disorder shift the optimum toward weaker noise and reduce the noise-optimized root-mean-square prediction error, with the largest reduction obtained for the bimodal case. These results identify stochastic forcing and quenched heterogeneity as coupled control parameters and show that the computational enhancement of LSMs depends on disorder structure rather than magnitude alone.
发表机构
- Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）
- Graz University of Technology（格拉茨工业大学）
机构由 AI 辅助整理，请以论文原文为准。
