随机神经网络中可自发出现吸引子合并与间歇现象。
Attractor-merging Crises and Intermittency in Reservoir Computing
- 通过调节全局参数，让随机网络生成吸引子合并与间歇行为。
- 发现该现象源于相空间结构的非线性演化，不依赖训练数据。
- 适用于各类随机神经网络，为动态建模提供新视角。
储层计算可将吸引子嵌入随机神经网络（RNNs），由于其固有的对称性约束，生成目标吸引子的“镜像”。在这些RNN中，我们报告仅通过调节全局参数即可引发伴随间歇性的吸引子合并危机。通过详细分析相空间结构，进一步揭示了其内在机制，并证明该分岔现象是广泛类RNN的固有特性，与训练数据无关。
原文摘要 · Abstract (English)
Reservoir computing can embed attractors into random neural networks (RNNs), generating a ``mirror'' of a target attractor because of its inherent symmetrical constraints. In these RNNs, we report that an attractor-merging crisis accompanied by intermittency emerges simply by adjusting the global parameter. We further reveal its underlying mechanism through a detailed analysis of the phase-space structure and demonstrate that this bifurcation scenario is intrinsic to a general class of RNNs, independent of training data.
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。