中文
相关论文

相关论文: Analytic solution of attractor neural networks on …

200 篇论文

We study a number of graph exploration problems in the following natural scenario: an algorithm starts exploring an undirected graph from some seed node; the algorithm, for an arbitrary node $v$ that it is aware of, can ask an oracle to…

数据结构与算法 · 计算机科学 2017-10-25 Flavio Chierichetti , Shahrzad Haddadan

Neural networks are nowadays both powerful operational tools (e.g., for pattern recognition, data mining, error correction codes) and complex theoretical models on the focus of scientific investigation. As for the research branch, neural…

无序系统与神经网络 · 物理学 2014-07-22 Elena Agliari , Adriano Barra , Andrea Galluzzi , Daniele Tantari , Flavia Tavani

Understanding the subgraph distribution in random networks is important for modelling complex systems. In classic Erdos networks, which exhibit a Poissonian degree distribution, the number of appearances of a subgraph G with n nodes and g…

统计力学 · 物理学 2009-11-10 S. Itzkovitz , R. Milo , N. Kashtan , G. Ziv , U. Alon

Search space is a key consideration for neural architecture search. Recently, Xie et al. (2019) found that randomly generated networks from the same distribution perform similarly, which suggests we should search for random graph…

机器学习 · 计算机科学 2020-01-01 Xin Zhou , Dejing Dou , Boyang Li

A common way to accelerate shortest path algorithms on graphs is the use of a bidirectional search, which simultaneously explores the graph from the start and the destination. It has been observed recently that this strategy performs…

We investigate topologically biased failure in scale-free networks with degree distribution $P(k) \propto k^{-\gamma}$. The probability $p$ that an edge remains intact is assumed to depend on the degree $k$ of adjacent nodes $i$ and $j$…

无序系统与神经网络 · 物理学 2009-11-13 Andre A. Moreira , Jose S. Andrade , Hans J. Herrmann , Joseph O. Indekeu

Recently, a framework for analyzing time series by constructing an associated complex network has attracted significant research interest. One of the advantages of the complex network method for studying time series is that complex network…

混沌动力学 · 物理学 2015-06-04 Ruoxi Xiang , Jie Zhang , Xiao-ke Xu , Michael Small

The purpose of this article is to introduce a new iterative algorithm with properties resembling real life bipartite graphs. The algorithm enables us to generate wide range of random bigraphs, which features are determined by a set of…

人工智能 · 计算机科学 2010-11-03 Szymon Chojnacki , Mieczysław Kłopotek

Several fundamental properties of real complex networks, such as the small-world effect, the scale-free degree distribution, and recently discovered topological fractal structure, have presented the possibility of a unique growth mechanism…

数据分析、统计与概率 · 物理学 2009-11-13 Liuhua Zou , Wenjiang Pei , Tao Li , Zhenya He , Yiuming Cheung

We studied the computational properties of an attractor neural network (ANN) with different network topologies. Though fully connected neural networks exhibit, in general, a good performance, they are biologically unrealistic, as it is…

统计力学 · 物理学 2007-05-23 Joaquin J. Torres , Miguel A. Munoz , J. Marro , P. L. Garrido

Network topology plays a key role in many phenomena, from the spreading of diseases to that of financial crises. Whenever the whole structure of a network is unknown, one must resort to reconstruction methods that identify the least biased…

数据分析、统计与概率 · 物理学 2015-06-09 Rossana Mastrandrea , Tiziano Squartini , Giorgio Fagiolo , Diego Garlaschelli

To provide a phenomenological theory for the various interesting transitions in restructuring networks we employ a statistical mechanical approach with detailed balance satisfied for the transitions between topological states. This enables…

统计力学 · 物理学 2007-05-23 Imre Derenyi , Illes Farkas , Gergely Palla , Tamas Vicsek

Methods connecting dynamical systems and graph theory have attracted increasing interest in the past few years, with applications ranging from a detailed comparison of different kinds of dynamics to the characterisation of empirical data.…

统计力学 · 物理学 2018-01-18 Marcello A. Budroni , Andrea Baronchelli , Romualdo Pastor-Satorras

Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers…

机器学习 · 计算机科学 2024-01-23 Jaeyoon Sim , Sooyeon Jeon , InJun Choi , Guorong Wu , Won Hwa Kim

Recurrence networks are a novel tool of nonlinear time series analysis allowing the characterisation of higher-order geometric properties of complex dynamical systems based on recurrences in phase space, which are a fundamental concept in…

混沌动力学 · 物理学 2016-04-07 Y. Zou , J. Heitzig , R. V. Donner , J. F. Donges , J. D. Farmer , R. Meucci , S. Euzzor , N. Marwan , J. Kurths

We present a new approach, the Topograph, which reconstructs underlying physics processes, including the intermediary particles, by leveraging underlying priors from the nature of particle physics decays and the flexibility of message…

高能物理 - 唯象学 · 物理学 2023-10-16 Lukas Ehrke , John Andrew Raine , Knut Zoch , Manuel Guth , Tobias Golling

Extensive studies have been done to understand the principles behind architectures of real networks. Recently, evidences for hierarchical organization in many real networks have also been reported. Here, we present a new hierarchical model…

其他凝聚态物理 · 物理学 2007-05-23 J. C. Nacher , N. Ueda , M. Kanehisa , T. Akutsu

Graph neural networks (GNNs) have gained prominence in recommendation systems in recent years. By representing the user-item matrix as a bipartite and undirected graph, GNNs have demonstrated their potential to capture short- and…

信息检索 · 计算机科学 2023-11-29 Daniele Malitesta , Claudio Pomo , Tommaso Di Noia

Random scale-free overlay topologies provide a number of properties like for example high resilience against failures of random nodes, small (average) diameter as well as good expansion and congestion characteristics that make them…

网络与互联网体系结构 · 计算机科学 2013-07-16 Ingo Scholtes

We study Ising spin models on finitely connected random interaction graphs which are drawn from an ensemble in which not only the degree distribution $p(k)$ can be chosen arbitrarily, but which allows for further fine-tuning of the topology…

无序系统与神经网络 · 物理学 2009-11-13 C. J. Perez-Vicente , A. C. C. Coolen