Redundant Hash Addressing of Feature Sequences Using the Self-Organizing Map

Kohonen's Self-Organizing Map (SOM) is combined with the Redundant Hash Addressing (RHA) principle. The SOM encodes the input feature vector sequence into the sequence of best-matching unit (BMU) indices and the RHA principle is then used to associate the BMU index sequence with the dictionary items. This provides a fast alternative for dynamic programming (DP) based methods for comparing and matching temporal sequences. Experiments include music retrieval and speech recognition. The separation of the classes can be improved by error-corrective learning. Comparisons to DP-based methods are presented.     

Decomposing the global financial crisis: A Self-Organizing Time Map

A key starting point for financial stability surveillance is understanding past, current and possible future risks and vulnerabilities. Through temporal data and dimensionality reduction, or visual dynamic clustering, this paper aims to present a holistic view of cross-sectional macro-financial patterns over time. The Self-Organizing Time Map (SOTM) is a recent adaptation of the Self-Organizing Map for exploratory temporal structure analysis, which disentangles cross-sectional data structures over time. We apply the SOTM, as well as its combination with classical cluster analysis, in financial stability surveillance. Thus, this paper uses the SOTM for decomposing and identifying temporal structural changes in macro-financial data before, during and after the global financial crisis of 2007–2009.     

一种高效的自组织特征映射图的初始化方法

自组织特征映射图算法(SOFM,self-organizing Feature Map)在模式识别中有着广泛的应用.本文首先讨论了网络结构的初始化设置对自组织特征映射图构造的影响以及加速SOFM网络学习训练过程的主要方法,然后提出一种从边界到中心的自组织特征映射图初始化方法,该方法形成的自组织特征映射图能够真实地表示输入样本内在关系,大大减少学习训练次数,从而有效改进了传统的SOFM算法.     

The Self-Organizing Map of Trees

In the standard version of the Self-Organizing Map, each neuron is associated with a vector. An extension using trees instead of vectors is presented. Compared to vectors, trees provide remarkably more degrees of freedom. The essential points of self-organization, the distance function and the learning rule, are adapted to trees by means of graph matching. In order to avoid exhaustive searching in tree matching an efficient heuristic is introduced. The results of the experiments are promising: the proposed methods apply elegantly in the process of self-organization.     

The Supervised Network Self-Organizing Map for Classification of Large Data Sets

Complex application domains involve difficult pattern classification problems. The state space of these problems consists of regions that lie near class separation boundaries and require the construction of complex discriminants while for the rest regions the classification task is significantly simpler. The motivation for developing the Supervised Network Self-Organizing Map (SNet-SOM) model is to exploit this fact for designing computationally effective solutions. Specifically, the SNet-SOM utilizes unsupervised learning for classifying at the simple regions and supervised learning for the difficult ones in a two stage learning process. The unsupervised learning approach is based on the Self-Organizing Map (SOM) of Kohonen. The basic SOM is modified with a dynamic node insertion/deletion process controlled with an entropy based criterion that allows an adaptive extension of the SOM. This extension proceeds until the total number of training patterns that are mapped to neurons with high entropy (and therefore with ambiguous classification) reduces to a size manageable numerically with a capable supervised model. The second learning phase (the supervised training) has the objective of constructing better decision boundaries at the ambiguous regions. At this phase, a special supervised network is trained for the computationally reduced task of performing the classification at the ambiguous regions only. The performance of the SNet-SOM has been evaluated on both synthetic data and on an ischemia detection application with data extracted from the European ST-T database. In all cases, the utilization of SNet-SOM with supervised learning based on both Radial Basis Functions and Support Vector Machines has improved the results significantly related to those obtained with the unsupervised SOM and has enhanced the scalability of the supervised learning schemes. The highly disciplined design of the generalization performance of the Support Vector Machine allows to design the proper model for the particular training set.     

基于多层自组织映射和主成分分析的入侵检测方法*

首先改进了自组织映射学习和分类算法,通过引入自定义变量匹配度、约简率和约简样本量化误差,提出了一种新的基于多层自组织映射和主成分分析入侵检测模型与算法。模型运用主成分分析算法对输入样本进行特征约简,运用分层思想对分类精度低的聚类进行逐层细分,解决了单层自组织映射分类不精确的问题。实验结果表明该模型用于入侵检测的效果良好,能准确区分攻击与否且能进一步指出攻击的具体类型。     

A Convolutional Deep Self-Organizing Map Feature extraction for machine learning

In this work we propose a new Unsupervised Deep Self-Organizing Map (UDSOM) algorithm for feature extraction, quite similar to the existing multi-layer SOM architectures. The principal underlying idea of using SOMs is that if a neuron is wins n times, these n inputs that activated this neuron are similar. The basic principle consists of an alternation of phases of splitting and abstraction of regions, based on a non-linear projection of high-dimensional data over a small space using Kohonen maps following a deep architecture. The proposed architecture consists of a splitting process, layers of alternating self-organizing, a rectification function RELU and an abstraction layer (convolution-pooling). The self-organizing layer is composed of a few SOMs with each map focusing on modelling a local sub-region. The most winning neurons of each SOM are then organized in a second sampling layer to generate a new 2D map. In parallel to this transmission of the winning neurons, an abstraction of the data space is obtained after the convolution-pooling module. The ReLU is then applied. This treatment is applied more than once, changing the size of the splitting window and the displacement step on the reconstructed input image each time. In this way, local information is gathered to form more global information in the upper layers by applying each time a convolution filter of the level. The architecture of the Unsupervised Deep Self-Organizing Map is unique and retains the same principle of deep learning algorithms. This architecture can be very interesting in a Big Data environment for machine learning tasks. Experiments have been conducted to discuss how the proposed architecture shows this performance.

     

Self-Organizing Map Oversampling (SOMO) for imbalanced data set learning

Learning from imbalanced datasets is challenging for standard algorithms, as they are designed to work with balanced class distributions. Although there are different strategies to tackle this problem, methods that address the problem through the generation of artificial data constitute a more general approach compared to algorithmic modifications. Specifically, they generate artificial data that can be used by any algorithm, not constraining the options of the user. In this paper, we present a new oversampling method, Self-Organizing Map-based Oversampling (SOMO), which through the application of a Self-Organizing Map produces a two dimensional representation of the input space, allowing for an effective generation of artificial data points. SOMO comprises three major stages: Initially a Self-Organizing Map produces a two-dimensional representation of the original, usually high-dimensional, space. Next it generates within-cluster synthetic samples and finally it generates between cluster synthetic samples. Additionally we present empirical results that show the improvement in the performance of algorithms, when artificial data generated by SOMO are used, and also show that our method outperforms various oversampling methods.     

Bringing Knowing-When and Knowing-What Together: Periodically Tuned Categorization and Category-Based Timing Modeled with the Recurrent Oscillatory Self-Organizing Map (ROSOM)

The study addresses the cyclically temporal aspect of sequence recognition, storage and recall using the Recurrent Oscillatory Self-Organizing Map (ROSOM), first introduced by Kaipainen, Papadopoulos and Karhu (1997). The unique solution of the network is that oscillatory States are assigned to network units, corresponding to their `readiness-to-fire'. The ROSOM is a categorizer, a temporal sequence storage system and a periodicity detector designed for use in an ambiguous cyclically repetitive environment. As its external input, the model accepts a multidimensional stream of environment-describing feature configurations with implicit periodicities. The output of the model is one or a few closed cycles abstracted from such a stream, mapped as trajectories on a two-dimensional sheet with an organization reminiscent of multi-dimensional scaling. The model's capabilities are explored with a variety of workbench data.     

Rough Self Organizing Map

A rough self-organizing map (RSOM) with fuzzy discretization of feature space is described here. Discernibility reducts obtained using rough set theory are used to extract domain knowledge in an unsupervised framework. Reducts are then used to determine the initial weights of the network, which are further refined using competitive learning. Superiority of this network in terms of quality of clusters, learning time and representation of data is demonstrated quantitatively through experiments over the conventional SOM.     

Piecewise Linear Projection Based on Self-Organizing Map

A piecewise linear projection algorithm, based on kohonen's Self-Organizing Map, is presented. Using this new algorithm, neural network is able to adapt its neural weights to accommodate with input space, while obtaining reduced 2-dimensional subspaces at each neural node. After completion of learning process, first project input data into their corresponding 2-D subspaces, then project all data in the 2-D subspaces into a reference 2-D subspace defined by a reference neural node. By piecewise linear projection, we can more easily deal with large data sets than other projection algorithms like Sammon's nonlinear mapping (NLM). There is no need to re-compute all the input data to interpolate new input data to the 2-D output space.     

Some measures to impact on the performance of Kohonen self-organizing map

Multimedia Tools and Applications - In the field of unsupervised learning, Self-Organizing Map (SOM) has attracted the attention of many researchers. SOM is a popular algorithm in the area of data...     

Simulated annealing technique for fast learning of SOM networks

The Self-Organizing Map (SOM) is a popular unsupervised neural network able to provide effective clustering and data visualization for multidimensional input datasets. In this paper, we present an application of the simulated annealing procedure to the SOM learning algorithm with the aim to obtain a fast learning and better performances in terms of quantization error. The proposed learning algorithm is called Fast Learning Self-Organized Map, and it does not affect the easiness of the basic learning algorithm of the standard SOM. The proposed learning algorithm also improves the quality of resulting maps by providing better clustering quality and topology preservation of input multi-dimensional data. Several experiments are used to compare the proposed approach with the original algorithm and some of its modification and speed-up techniques.     

基于泛化竞争和局部渗透机制的自组织网TSP问题求解方法

旅行商问题(TSP)是组合优化中最典型的NP完全问题之一,具有很强的工程背景和应用价值.文章在分析了标准SOM(Self-Organizing Map)算法在求解TSP问题的不足和在寻求总体最优解的潜力的基础上,引入泛化竞争和局部渗透这两个新的学习机制,提出了一种新的SOM算法---渗透的SOM(Infiltrative SOM,ISOM)算法.通过泛化竞争和局部渗透策略的协同作用:总体竞争和局部渗透并举、先倾向总体竞争后倾向局部渗透、在总体竞争基础上的局部渗透,实现了在总体路径寻优指导下的局部路径优化,从而使所得路径尽可能接近最优解.通过对TSPLIB中14组TSP实例的测试结果及与KNIES、SETSP、Budinich和ESOM等类SOM算法的比较,表明该算法既简单又能使解的质量得到很大提高,同时还保持了解的良好的稳健特性.     

SOM neural network design – A new Simulink library based approach targeting FPGA implementation

The paper presents a method for FPGA implementation of Self-Organizing Map (SOM) artificial neural networks with on-chip learning algorithm. The method aims to build up a specific neural network using generic blocks designed in the MathWorks Simulink environment. The main characteristics of this original solution are: on-chip learning algorithm implementation, high reconfiguration capability and operation under real time constraints. An extended analysis has been carried out on the hardware resources used to implement the whole SOM network, as well as each individual component block.     

自组织映射在Web结构挖掘中的应用

该文讨论了用自组织映射进行Web结构挖掘的基本方法。用SOM可直观地表示数据的相似性和进行分类,还可方便地进行数据聚簇分析,并可在Web挖掘中找到权威页面等有用信息。     

基于SOM网络的语音训练可视化方法研究

提出了一种利用SOM网络输出层可视化的特点进行语音训练的方法。SOM网络能够将输入向量映射到二维平面或曲面上,受试者通过视觉反馈的位置信息,指导其发音行为。为了提高SOM聚类效果,SOM还进行加强训练;讨论了SOM输出层神经元个数对聚类的影响。实验结果表明,提出的利用SOM语音训练方法,直观简单,能够有效地实现“看图说话”。     

利用模糊神经网络实现逆向工程中的区域分割

论文提出了一种改进的模糊自组织特征映射网络(fuzzySOFM),它不仅显著加快了聚类的速度,而且算法简单。该网络采用由数据点的坐标、估算出的法矢量和曲率构成的八维特征向量作为输入,快速地实现了逆向工程中点云数据的区域分割。与现有方法相比,该方法具有以下优点:第一,具有更高的聚类速度,并可以直接处理含噪声数据;第二,聚类的结果与数据输入的顺序无关;第三,能利用数据的隶属度快速提取出特征线数据,从而将基于面的分割和基于线的分割结合起来。实验结果证明了这种方法的有效性。     

Homicide and Its Social Context: Analysis Using the Self-Organizing Map

Homicide is one of the most serious kinds of offenses. Research on causes of homicide has never reached a definite conclusion. The purpose of this article is to put homicide in its broad range of social context to seek correlation between this offense and other macroscopic socioeconomic factors. This international-level comparative study used a dataset covering 181 countries and 69 attributes. The data were processed by the Self-Organizing Map (SOM) assisted by other clustering methods, including ScatterCounter for attribute selection, and several statistical methods for obtaining comparable results. The SOM is found to be a useful tool for mapping criminal phenomena through processing of multivariate data, and correlation can be identified between homicide and socioeconomic factors.     

多光谱遥感数据直接分类变化检测的神经网络方法研究

变化检测是近年发展起来的一种遥感时序数据处理方法,用于识别遥感数据在不同时间所记录的地表变化信息。采用传统的基于统计学的分类算法检测两个时期多波段遥感数据变化信息时,如果采取直接分类变化检测的方法会出现统计数据结构的奇异性问题,表现在同一位置上出现不同的光谱特征值。因此,该文提出和实验了使用基于样本和数据权重的自组织特征映射神经网络(SOFM)直接分类检测变化信息的方法。结果表明,SOFM直接分类变化检测法与两个时期最大似然方法分类后相减的结果相比,检测精度有显著提高。