用小规模模型复现复杂网络任意节点动态，故障节点可替换
Versatile Reservoir Computing for Heterogeneous Complex Networks
- 用少量节点时序训练小型储备池，泛化到全网络任意节点
- 替换故障节点后，网络整体动态在有限时间内保持准确
- 适用于不同参数和连接性的振子与混沌系统，适合工程容错设计
提出一种新型通用储备池计算方法，用于维持异质复杂网络的动力学。我们证明，仅需对网络中部分元素的时序数据进行训练，一个小型储备池计算机即可复现大规模网络中任意元素的动力学行为，即使这些元素具有不同的内在参数和连通性。进一步地，通过用训练好的机器替代失效节点，我们展示了网络集体动力学可在有限时间范围内被精确保留。该方案在三个典型网络模型上得到验证：非同质相位振子构成的同质复杂网络、非同质相位振子构成的异质复杂网络，以及非同质混沌振子构成的异质复杂网络。
原文摘要 · Abstract (English)
A new machine learning scheme, termed versatile reservoir computing, is proposed for sustaining the dynamics of heterogeneous complex networks. We show that a single, small-scale reservoir computer trained on time series from a subset of elements is able to replicate the dynamics of any element in a large-scale complex network, though the elements are of different intrinsic parameters and connectivities. Furthermore, by substituting failed elements with the trained machine, we demonstrate that the collective dynamics of the network can be preserved accurately over a finite time horizon. The capability and effectiveness of the proposed scheme are validated on three representative network models: a homogeneous complex network of non-identical phase oscillators, a heterogeneous complex network of non-identical phase oscillators, and a heterogeneous complex network of non-identical chaotic oscillators.
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。