Robust Growing Hierarchical Self Organizing Map

IEEE Transactions on Neural Networks, 2000

Since the introduction of the Growing Hierarchical Self-Organizing Map (GHSOM) much work has been done on selforganizing neural models with a dynamic structure. These models allow adjusting the layers of the model to the features of the input dataset. Here we propose a new self-organizing model which is based on a probabilistic mixture of multivariate Gaussian components. The learning rule is derived from the stochastic approximation framework, and a probabilistic criterion is used to control the growth of the model. Moreover, the model is able to adapt the topology of each layer, so that a hierarchy of dynamic graphs is built. This overcomes the limitations of the self-organizing maps with a fixed topology, and gives rise to a faithful visualization method for high dimensional data.

2007 IEEE International Conference on Systems, Man and Cybernetics, 2007

The growing Recurrent Self-Organizing Map (GRSOM) is embedded into a standard Self-Organizing Map (SOM) hierarchy. To do so, the KDD benchmark dataset from the International Knowledge Discovery and Data Mining Tools Competition is employed. This dataset consists of 500,000 training patterns and 41 features for each pattern. Unlike most of the previous methods, only 6 of the basic features are employed. The resulting model has a capability of detection (false positive) rate of 89.6% (5.66%), where this is as good as the data-mining approaches that uses all 41 features and twice as faster than a similar hierarchical SOM architecture.

2000

The growing self-organizing map (GSOM) has been presented as an extended version of the self-organizing map (SOM), which has significant advantages for knowledge discovery applications. In this paper, the GSOM algorithm is presented in detail and the effect of a spread factor, which can be used to measure and control the spread of the GSOM, is investigated. The spread factor is independent of the dimensionality of the data and as such can be used as a controlling measure for generating maps with different dimensionality, which can then be compared and analyzed with better accuracy. The spread factor is also presented as a method of achieving hierarchical clustering of a data set with the GSOM. Such hierarchical clustering allows the data analyst to identify significant and interesting clusters at a higher level of the hierarchy, and as such continue with finer clustering of only the interesting clusters. Therefore, only a small map is created in the beginning with a low spread factor, which can be generated for even a very large data set. Further analysis is conducted on selected sections of the data and as such of smaller volume. Therefore, this method facilitates the analysis of even very large data sets.

2010

This paper presents a novel architecture of SOM which organizes itself over time. The proposed method called MIGSOM (Multilevel Interior Growing Self-Organizing Maps) which is generated by a growth process. However, the network is a rectangular structure which adds nodes from the boundary as well as the interior of the network. The interior nodes will be added in a superior level of the map. Consequently, MIGSOM can have three-Dimensional structure with multi-levels oriented maps. A performance comparison of three Self-Organizing networks, the Kohonen feature Map (SOM), the Growing Grid (GG) and the proposed MIGSOM is made. For this purpose, the proposed method is tested with synthetic and real datasets. Indeed, we show that our method (MIGSOM) improves better performance for data quantification and topology preservation with similar map size of GG and SOM.

Knowledge-Based Systems, 2019

The Self-Organizing Map (SOM) has attracted much research in diverse fields of study, where it has been successfully applied to a wide range of artificial intelligence applications. In this paper, a new intelligent adaptive learning SOM, in contrast with the conventional SOM algorithm, is presented. The proposed SOM overcomes the disadvantages of the conventional SOM by deriving a new variable learning rate that can adaptively achieve the optimal weights and obtain the winner neurons with a shorter learning process time. To quantify the performance, the proposed SOM was compared with various unsupervised algorithms to examine how well the network weight update equation adapts and reaches the optimum weights with fewer iterations. Extensive experiments were conducted using eight different databases from the UCI and KEEL repositories. The proposed SOM algorithm was further compared with the conventional SOM, GF-SOM, PLSOM, and PLSOM2 algorithms. The proposed SOM algorithm showed superiority in terms of the convergence rate, Quantization Error (QE), Topology Error (TE) preserving map, and accuracy during the classification process.

IEEE transactions on neural networks and learning systems, 2020

Self-organizing maps (SOMs) are aimed to learn a representation of the input distribution which faithfully describes the topological relations among the clusters of the distribution. For some data sets and applications, it is known beforehand that some regions of the input space cannot contain any samples. Those are known as forbidden regions. In these cases, any prototype which lies in a forbidden region is meaningless. However, previous self-organizing models do not address this problem. In this paper, we propose a new SOM model which is guaranteed to keep all prototypes out of a set of prespecified forbidden regions. Experimental results are reported, which show that our proposal outperforms the SOM both in terms of vector quantization error and quality of the learned topological maps.

Lecture Notes in Computer Science, 2014

The paper deals with the high dimensional data clustering problem. One possible way to cluster this kind of data is based on Artificial Neural Networks (ANN) such as Growing Neural Gas (GNG) or Self Organizing Maps (SOM). The learning phase of ANN, which is time-consuming especially for large high-dimensional datasets, is the main drawback of this approach to data clustering. Parallel modification, Growing Neural Gas with pre-processing by Self Organizing Maps, and its implementation on the HPC cluster is presented in the paper. Some experimental results are also presented.

Neurocomputing, 2011

The Self-Organizing Map (SOM) is a neural network model that performs an ordered projection of a high dimensional input space in a low-dimensional topological structure. The process in which such mapping is formed is defined by the SOM algorithm, which is a competitive, unsupervised and nonparametric method, since it does not make any assumption about the input data distribution. The feature maps provided by this algorithm have been successfully applied for vector quantization, clustering and high dimensional data visualization processes. However, the initialization of the network topology and the selection of the SOM training parameters are two difficult tasks caused by the unknown distribution of the input signals. A misconfiguration of these parameters can generate a feature map of low-quality, so it is necessary to have some measure of the degree of adaptation of the SOM network to the input data model. The topology preservation is the most common concept used to implement this measure. Several qualitative and quantitative methods have been proposed for measuring the degree of SOM topology preservation, particularly using Kohonen's model. In this work, two methods for measuring the topology preservation of the Growing Cell Structures (GCSs) model are proposed: the topographic function and the topology preserving map.

2016

Dr. D. Hari Prasad Professor, Department of Computer Applications, SNR Sons College, Coimbatore Abstract A primary drawback of the traditional SOM is that the size of the mapis fixed and the number of neurons in the map should be determined a priori. This might not be feasible for some applications and result in a significant limitation on the final mapping. Several dynamic SOM models have been proposed recently to reduce the limitations of the fixed network architecture of the traditional SOM. These models rely on an adaptive architecture where neurons and connections are inserted into or removed from the map during their learning process according to the particular requirements of the input data. A major variation of traditional SOM model is proposed in this paper.