网络的策略演化模型及其在知识交流网络结构仿真中的应用

为了验证网络战略演化模型能够生成呈现大部分真实社会网络主要结构特性的网络,并探索知识缄默性对网络结构的影响规律,为此,引入空间动态连接模型来描述代理人之间连接的策略模式,运用时间非齐次的马尔可夫随机过程来刻画网络动态演化过程,进而利用动力学仿真研究知识缄默性对网络结构的影响规律。结果显示,当衰减参数处于区间[0.35,0.7]时,网络呈现集聚性,并且只有很少的代理人维持长连接;当代理人之间连接成本呈正态分布时,度的分布是非对称的。事实上,此时的网络呈现出了小世界特性。     

加权Fast Newman模块化算法在人脑结构网络中的应用

针对二值人脑结构网络的模块化方法不足以反映复杂的人脑生理特征这一问题,提出一种基于Fast Newman二值算法的加权脑网络模块化算法。该算法以凝聚节点的层次聚类思想为基础,以脑网络中单个脑区节点的权重值和脑网络总权重值为主要依据构建加权模块度评价指标,并将其增量作为度量值来确定加权脑网络中节点的合并从而实现模块划分。将该算法应用于60个健康人的组平均数据中的实验结果显示,与二值人脑网络模块化结果相对比,所提算法得到的模块度提高了28%,并且模块内部和模块外部的特征区分更加明显,所得到的人脑模块也更符合已知的人脑生理特性;而与现有的两种加权模块化算法实验对比结果表明,所提算法在合理划分人脑网络模块结构的同时也小幅提高了模块度。     

Incremental Learning with Respect to New Incoming Input Attributes

Neural networks are generally exposed to a dynamic environment where the training patterns or the input attributes (features) will likely be introduced into the current domain incrementally. This Letter considers the situation where a new set of input attributes must be considered and added into the existing neural network. The conventional method is to discard the existing network and redesign one from scratch. This approach wastes the old knowledge and the previous effort. In order to reduce computational time, improve generalization accuracy, and enhance intelligence of the learned models, we present ILIA algorithms (namely ILIA1, ILIA2, ILIA3, ILIA4 and ILIA5) capable of Incremental Learning in terms of Input Attributes. Using the ILIA algorithms, when new input attributes are introduced into the original problem, the existing neural network can be retained and a new sub-network is constructed and trained incrementally. The new sub-network and the old one are merged later to form a new network for the changed problem. In addition, ILIA algorithms have the ability to decide whether the new incoming input attributes are relevant to the output and consistent with the existing input attributes or not and suggest to accept or reject them. Experimental results show that the ILIA algorithms are efficient and effective both for the classification and regression problems.     

类脑超大规模深度神经网络系统

大规模神经网络展现出强大的端到端表示能力和非线性函数的无限逼近能力,在多个领域表现出优异的性能,成为一个重要的发展方向.如自然语言处理(NLP)模型GPT,经过几年的发展,目前拥有1750亿网络参数,在多个NLP基准上到达最先进性能.然而,按照现有的神经网络组织方式,目前的大规模神经网络难以到达人脑生物神经网络连接的规...     

基于同步多维数据流的脑网络动态特征辨识方法研究

针对人脑实时变化的特性,为了更好的观测和描述人脑网络的动态特征,在基于功能磁共振成像的脑功能网络重构技术基础上,给出了一种人脑网络动态特征辨识方法。首先利用同步多维数据流的即时更新能力,将在静息态功能磁共振成像数据采集区间上的血氧水平依赖信号由大时间序列分解重构为每个采样点上的小时间窗口序列,构建连续时间点上的状态观测窗口,从而实现对人脑功能共振信号的特定时间状态辨识,然后运用相关分析对状态观测窗口信号进行分析,得到单状态观测矩阵,最终构建全脑在整个数据采集区间上的动态特征矩阵。实验结果显示该方法可以为人脑网络的动态特征观测和描述提供一种有效手段,也为进一步研究人脑网络的动态特征演变奠定了基础。     

动态复杂供需网络局域演化模型的研究

为了深入理解供需网络的演化规律,研究了已有的复杂网络演化模型刻画供需网络生长过程的不足,提出了以星型网络表示初始网络,在局域世界中选择新增节点的连接节点,局域世界的选取,采用了依据节点之间的网络路径值作为选取局域世界的原则,同时定义了局域世界的规模动态增长,从而建立了复杂供需网络的动态演化模型,并给出了生成模型的算法。该模型在考虑网络动态增长的同时,也考虑到网络内部边的动态演化以及节点的退出,这与现实情况相吻合,因此更细致、真实地刻画了供需网络的动态演化特性。仿真结果表明,该模型所生成的网络模型具有无标度特性和小世界性。     

Natural image statistics and efficient coding

Natural images contain characteristic statistical regularities that set them apart from purely random images. Understanding what these regularities are can enable natural images to be coded more efficiently. In this paper, we describe some of the forms of structure that are contained in natural images, and we show how these are related to the response properties of neurons at early stages of the visual system. Many of the important forms of structure require higher-order (i.e. more than linear, pairwise) statistics to characterize, which makes models based on linear Hebbian learning, or principal components analysis, inappropriate for finding efficient codes for natural images. We suggest that a good objective for an efficient coding of natural scenes is to maximize the sparseness of the representation, and we show that a network that learns sparse codes of natural scenes succeeds in developing localized, oriented, bandpass receptive fields similar to those in the mammalian striate cortex.     

一种动态的移动社交网络拓扑模型

针对移动社交网络的动态性、用户不同重要性和信息交互有向性,基于4种初始网络提出能准确描述移动社交网络结构的拓扑模型。采用随机游走理论和改进的PageRank算法,引入过渡概率使每两时步之间的网络拓扑结构相互联系。通过PageRank算法得到节点的势,进而求出概率过渡矩阵,利用随机游走理论由上一时步边存在概率矩阵和概率过渡矩阵得到当前时步边存在概率矩阵,每一时步动态地增加一个节点并检验是否有离开的节点。仿真结果显示,该模型在4种初始网络下得到的网络拓扑结构,入度、出度、势分布以及度-势相关性均具有明显幂律特性,表明随机游走理论和改进的PageRank算法能较准确描述移动社交网络,具有一定的实践意义。     

基于时间自动机的脑网络时空演化建模方法

人类大脑本质上是不断变化的整体,但基于静息态功能磁共振成像重构技术的人脑网络动态特性研究尚在起步阶段,并且大多采用定性的方法描述。采用时间自动机理论对脑网络在时间和空间上的系统动态特征和演化过程展开了建模方法研究,首先通过对采样时间区间上血氧依赖水平信号的处理得到全脑脑区在单个采样点上的状态描述,然后通过无监督聚类获取其状态集,研究其状态随时间转换的可观测性,最后在此基础上结合时间自动机理论对脑网络状态的演化过程进行建模,从而达到对脑网络动态特性定量描述的目的。实验结果显示该方法可定量描述人脑网络的状态转换规律和演变进程,对不同被试数据具有普适性,并且可辨识出被试的异常演化过程,为脑网络动态特性的深入研究提供了理论基础。     

基于图约简的知识联想关系网络建模

考虑到人类知识在大脑中以联想记忆形式存在，尝试从联想关系的视角深入探索知识体系的内在关系网络模型，旨在为知识图谱的建模提供一种可参考的新思路。对于给定的知识语料库，首先考虑以直接联想关系生成方式构建初始的知识关系网络，随后引入多种图约简方法优化知识联想关系网络的建模。研究中特别地提出了随机选择、局部联想最大记忆保留、全局联想最大记忆保留等3种知识联想关系约简重整策略，并通过实验手段对这3种策略进行建模分析。实验结果表明:3种方法呈现出了价值意义清晰的共同性能特征，而其中的全局联想最大记忆保留策略能最优地平衡知识联想关系网络的规模和联想记忆效率，可为相关应用提供有效的方法基础，也可为进一步探索类脑联想记忆的知识关系网络生成建模提供十分有益的启发。     

一种基于流立方体的网络安全态势感知模型

网络安全态势感知是网络安全监控技术一个新的发展方向,对网络安全态势的掌握对于网络安全而言具有重要的意义。在已有的关于数据立方体模型的研究基础之上,本文提出了一种基于流立方体模型的网络安全态势感知模型,以描述和抽象化网络安全态势感知中涉及的多维分析结构,从网络安全事件统计数据流的数据特征出发分析网络安全态势。给出了基于频率、趋势和熵值这三种数据特征的模型实例,利用流立方体相邻层次间单元的关系证明了这三种数据特征可以只从原始数据计算底层单元的特征,而上层单元的数据特征则可以通过对底层数据特征的运算而直接得到,从而实现高效计算。实际应用系统的构建和利用网络安全数据的测试实验表明了所提模型和方法的有效性。     

Predicting Resting-state Functional Connectivity With Efficient Structural Connectivity

The complex relationship between structural connectivity (SC) and functional connectivity (FC) of human brain networks is still a critical problem in neuroscience. In order to investigate the role of SC in shaping resting-state FC, numerous models have been proposed. Here, we use a simple dynamic model based on the susceptible-infected-susceptible (SIS) model along the shortest paths to predict FC from SC. Unlike the previous dynamic model based on SIS theory, we focus on the shortest paths as the principal routes to transmit signals rather than the empirical structural brain network. We first simplify the structurally connected network into an efficient propagation network according to the shortest paths and then combine SIS infection theory with the efficient network to simulate the dynamic process of human brain activity. Finally, we perform an extensive comparison study between the dynamic models embedded in the efficient network, the dynamic model embedded in the structurally connected network and dynamic mean field (DMF) model predicting FC from SC. Extensive experiments on two different resolution datasets indicate that ⅰ) the dynamic model simulated on the shortest paths can predict FC among both structurally connected and unconnected node pairs; ⅱ) though there are fewer links in the efficient propagation network, the predictive power of FC derived from the efficient propagation network is better than the dynamic model simulated on a structural brain network; ⅲ) in comparison with the DMF model, the dynamic model embedded in the shortest paths is found to perform better to predict FC.      

A model for reasoning about persistence and causation

Reasoning about change requires predicting how long a proposition, having become true, will continue to be so. Lacking perfect knowledge, an agent may be constrained to believe that a proposition persists indefinitely simply because there is no way for the agent to infer a contravening proposition with certainty. In this paper, we describe a model of causal reasoning that accounts for knowledge concerning cause-and-effect relationships and knowledge concerning the tendency for propositions to persist or not as a function of time passing. Our model has a natural encoding in the form of a network representation for probabilistic models. We consider the computational properties of our model by reviewing recent advances in computing the consequences of models encoded in this network representation. Finally, we discuss how our probabilistic model addresses certain classical problems in temporal reasoning (e. g., the frame and qualification problems).     

LDNet: Lightweight dynamic convolution network for human pose estimation

Lightweight implementation of existing human pose estimation networks limits the model representation capability, and it cannot effectively deal with problems such as changeable poses, complex backgrounds, and occlusion in practical applications. To address this problem, a lightweight human pose estimation network with dynamic convolution, called LDNet, is proposed in this study. First, we start from a lightweight feature extraction head to reduce the number of image preprocessing parameters. Then, we employ a high-resolution parallel subnetwork to predict precise keypoint heatmaps. To reduce the complexity due to high-resolution representations while maintaining good network performance, we propose a lightweight dynamic convolution. It can cope with changing human poses by adaptively learning different convolution parameters. Finally, to further exploit the relationship between the high-level semantic and spatial structure features for accurately locating different keypoints, we propose a keypoint refinement module based on our lightweight dynamic convolution to improve the keypoint detection and location results. Overall, accurate keypoint prediction results are obtained and compared with those of many existing networks, such as HRNet, the number of parameters is reduced by 82.1% and the calculation complexity is reduced by 47.9%. The model achieves an average precision of 73.5% and 88.7% on the COCO 2017 and MPII datasets, respectively. LDNet also shows good prediction accuracy and robustness on the CrowdPose dataset. The proposed network is superior to existing outstanding lightweight networks and is comparable to existing large-scale human pose estimation networks.     

Microscale and mesoscale discrete models for dynamic fracture of structures built of brittle material

In this work we present the discrete models for dynamic fracture of structures built of brittle materials. The models construction is based on Voronoi cell representation of the heterogeneous structure, with the beam lattice network used to model the cohesive and compressive forces between the neighboring cells. Each lattice component is a geometrically exact shear deformable beam which can describe large rigid body motion and the most salient fracture mechanisms. The latter can be represented through the corresponding form of the beam constitutive equations, which are derived either at microscale with random distribution of material properties or at a mesoscale with average deterministic values. The proposed models are also placed within the framework of dynamics, where special attention is paid to constructing the lattice network mass matrix as well as the corresponding time-stepping schemes. Numerical simulations of compression and bending tests is given to illustrate the models performance.     

基于卷积块注意力模块的图像描述生成模型

图像描述生成模型是使用自然语言描述图片的内容及其属性之间关系的算法模型.对现有模型描述质量不高、图片重要部分特征提取不足和模型过于复杂的问题进行了研究,提出了一种基于卷积块注意力机制模块(CBAM)的图像描述生成模型.该模型采用编码器-解码器结构,在特征提取网络Inception-v4中加入CBAM,并作为编码器提取图片的重要特征信息,将其送入解码器长短期记忆网络(LSTM)中,生成对应图片的描述语句.采用MSCOCO2014数据集中训练集和验证集进行训练和测试,使用多个评价准则评估模型的准确性.实验结果表明,改进后模型的评价准则得分优于其他模型,其中Model2实验能够更好地提取到图像特征,生成更加准确的描述.     

面向阿尔茨海默病的脑网络多频融合图核

复杂网络分析与机器学习方法相结合的阿尔茨海默病辅助诊断研究受到了越来越多的关注,其通常采用脑功能网络的方法来描述大脑活动的信息.然而,现有的成果大多基于时域信号匹配构建脑功能网络,忽略了脑活动信息在各个频段下的差异.因此,本文提出了脑网络多频融合图核的阿尔茨海默病诊断方法.首先,将功能磁共振成像产生的图像通过小波变换的方法进行分频段处理;其次,分别计算得到的各频段图像中任意两个脑区间的互信息,并设定阈值与互信息值进行比较进而构造出多频脑网络模型;然后,基于此提出面向多频脑网络模型的融合图核;最后,基于多频融合图核、采用核极限学习机在ADNI(Alzheimer’s Disease Neuroimaging Initiative)公开数据库中获取的一组数据以及在OASIS(Open Access Series of Imaging Studies)公开数据库上获取的一组数据进行阿尔茨海默病的诊断.同时,还通过实验验证了不同参数设置对诊断结果的影响.两组数据集的实验结果表明,提出的多频融合图核的辅助诊断方法能够取得最佳性能,且该方法的辅助诊断准确率在两种数据集上比对比方法的最好结果分别提高了13.79%和15.29%.     

虚拟雪景的构造与仿真

如何模拟具有动态性、不规则性和随机性的自然雪景是当前虚拟现实领域研究的热点,采用位移映射构造近处多边形构造的雪块的方法,采用3ds Max创建雪景模型,导入OpenGL中加纹理映射,结合VC++2010的程序编写,以较小的系统资源消耗达到了更加实时逼真的效果,实现了整片雪花飘荡效果和虚拟雪景的真实模拟,为相关领域的动画模拟研究提供了新的思路。     

Superimposing neural learning by dynamic and spatial changing weights

In this article, a new neural network model is presented for incremental learning tasks where networks are required to learn new knowledge without forgetting the old. An essential core of the proposed network structure is their dynamic and spatial changing connection weights (DSCWs). A learning scheme is developed for the formulation of the dynamic changing weights, while a structural adaptation is formulated by the spatial changing connecting weights. To avoid disturbing the old knowledge by the creation of new connections, a restoration mechanism is introduced dusing the DSCWs. The usefulness of the proposed model is demonstrated by using a system identification task. This work was presented in part at the 7th International Symposium on Artificial Life and Robotics, Oita, Japan, January 16–18, 2002.     

基于稀疏贝叶斯算法的演化博弈网络重构

演化博弈是自然和社会系统中一种常见的互动类型,探知演化博弈网络的拓扑结构是理解其功能和集体行为的基础。对于演化博弈网络,个体的博弈行为通常难以用动力学方程进行描述,而且相关的时序信息一般数量有限并且是离散的,因此在有限的个体博弈信息下重构网络的结构有着重要的研究意义。本文基于稀疏贝叶斯学习方法进一步发展了演化博弈网络的重构方法,通过在随机网络和小世界网络上的数值模拟验证该方法的有效性。与先前的基于L1范数的方法相比,该方法同样能够在较少的个体博弈信息下实现网络的重构,并且具有更高的重构效率和更强的噪声鲁棒性。