通过自适应性增强神经网络性能
Enhancing neural-network performance via assortativity
摘要：
吸引子神经网络的性能已被证明是关键取决于底层拓扑结构的异质性。我们通过研究度-度相关性-或重复性-对神经网络行为的影响来进一步分析。我们利用最近提出的一种方法来研究相关的网络和动力学，分析和计算，这是独立的拓扑结构可能已经演变。我们展示了如何大大增强了对噪声的鲁棒性的互逆（正相关）神经网络，特别是如果它是存储信息的中枢神经元。
英文摘要：
The performance of attractor neural networks has been shown to depend crucially on the heterogeneity of the underlying topology. We take this analysis a step further by examining the effect of degree-degree correlations -- or assortativity -- on neural-network behavior. We make use of a method recently put forward for studying correlated networks and dynamics thereon, both analytically and computationally, which is independent of how the topology may have evolved. We show how the robustness to noise is greatly enhanced in assortative (positively correlated) neural networks, especially if it is the hub neurons that store the information.
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。
