arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.12895q-bio.NCcond-mat.dis-nncs.NAmath-phmath.MPmath.NAnlin.AO
收藏

随机图与无标度图中 Hopfield 型神经模型的时间复杂性

Temporal Complexity of a Hopfield-Type Neural Model in Random and Scale-Free Graphs

Marco Cafiso, Paolo Paradisi

AI总结:

本文采用 IDC 方法分析受生物启发的 Hopfield 型神经网络,比较无标度与随机拓扑,发现随机网络在不同噪声等参数下也可产生类似复杂性特征。

摘要:

Hopfield 网络模型及其推广形式最初是作为联想记忆(或称按内容寻址记忆)模型而被提出的。它们既被作为人工智能中的无监督学习方法,也被作为计算神经科学中的生物神经动力学模型而受到广泛研究。过去二十年来,生物神经网络的复杂性特征引起了科学界的兴趣。近年来,借自复杂网络理论的概念和工具被应用于人工神经网络与学习过程,从而使研究重点集中在拓扑方面。然而,时间结构同样是生物神经网络展现出的一项关键属性,并在表现出复杂间歇性的系统框架内得到研究。间歇性驱动复杂性(Intermittency-Driven Complexity,IDC)方法确实聚焦于自组织状态的亚稳态,其标志是事件间时间分布中的幂律衰减,或相关事件驱动扩散过程中的标度行为。对神经动力学中的 IDC 及其与网络拓扑之间关系的研究仍处于早期阶段。在本工作中,我们展示了对一个受生物启发的 Hopfield 型神经网络进行 IDC 分析所获得的初步结果,比较了两种不同的连接性,即无标度网络拓扑与随机网络拓扑。我们发现,随机网络能够触发与无标度网络相似的复杂性特征,尽管二者存在一些差异,并且这些特征出现在不同的参数取值下,尤其是在不同的噪声水平下。

英文摘要:

The Hopfield network model and its generalizations were introduced as a model of associative, or content-addressable, memory. They were widely investigated both as an unsupervised learning method in artificial intelligence and as a model of biological neural dynamics in computational neuroscience. The complexity features of biological neural networks have attracted the scientific community's interest for the last two decades. More recently, concepts and tools borrowed from complex network theory were applied to artificial neural networks and learning, thus focusing on the topological aspects. However, the temporal structure is also a crucial property displayed by biological neural networks and investigated in the framework of systems displaying complex intermittency. The Intermittency-Driven Complexity (IDC) approach indeed focuses on the metastability of self-organized states, whose signature is a power-decay in the inter-event time distribution or a scaling behaviour in the related event-driven diffusion processes. The investigation of IDC in neural dynamics and its relationship with network topology is still in its early stages. In this work, we present the preliminary results of an IDC analysis carried out on a bio-inspired Hopfield-type neural network comparing two different connectivities, i.e., scale-free vs. random network topology. We found that random networks can trigger complexity features similar to that of scale-free networks, even if with some differences and for different parameter values, in particular for different noise levels

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。

↑