In this paper, we describe a self-organizing neural network model that
addresses the process of early lexical acquisition in young children. The growing lexicon is modeled by combined semantic word representations based on distributional statistics of words and on grounded semantic features of words. Changing semantic word representations are assumed to model the maturation of word meaning and serve as inputs to the growing semantic map. The model has been tested on a real child-directed parental language corpus and as a result, the map demonstrates the emergence and reorganization of various word categories, as quantified by two measures.
For the data sampled from a low-dimensional nonlinear manifold embedded in a high-dimensional space, such as Swiss roll and S-curve, Self-Organizing Map (SOM) tends to get stuck in local minima and then yield topological defects in the final map. To avoid this problem and obtain more faithful visualization results, a variant of SOM, i.e. Dynamic Self-Organizing Map (DSOM), was presented in this paper. DSOM can dynamically increase the map size, as the training data set is expanded according to its intrinsic neighborhood structure, starting from a small neighborhood in which the data points can lie on or close to a linear patch. According to the locally Euclidean nature of the manifold, the map can be guided onto the manifold surface and then the global faithful visualization results can be achieved step by step. Experimental results show that DSOM can discover the intrinsic manifold structure of the data more faithfully than SOM. In addition, as a new manifold learning method, DSOM can obtain more concise visualization results and be less sensitive to the neighborhood size and the noise than typical manifold learning methods, such as Isometric Mapping (ISOMAP) and Locally Linear Embedding (LLE), which can also be verified by experimental results.
In the paper, an algorithm that allows to detect and reject outliers in a self-organizing map (SOM) has been proposed. SOM is used for data clustering as well as dimensionality reduction and the results obtained are presented in a special graphical form. To detect outliers in SOM, a genetic algorithm-based travelling salesman approach has been applied. After outliers are detected and removed, the SOM quality has to be estimated. A measure has been proposed to evaluate the coincidence of data classes and clusters obtained in SOM. A larger value of the measure means that the distance between centers of different classes in SOM is longer and the clusters corresponding to the data classes separate better. With a view to illustrate the proposed algorithm, two datasets (numerical and textual) are used in this investigation.
The Hypercolumri (HCM) neural network model is an unsupervised
competitive network consisting of hierarchical layers of the Hierarchical Self-Organizing Map (HSOM) neural networks arranged by similar to the cell planes in the Neocognitron (NC) neural network. The HCM model combines the advantages of both the HSOM and the NC while rejecting their disadvantages, and alleviates many difficulties associated with image recognition applications. It can recognize images with variant objects size, position, orientation, and spatial resolution. However, due to the hierarchical structure of the HCM model, the network spends a long tirne in the recognition. In this paper, the HCM model is introduced with a new competitive algorithm that reduces the network recognition tinie into a realtime range. The proposed algorithm uses the subset frorri the most discriminate codebook of the network weights to find the winner of each HSOM in the hrst layer of the HCM model.
From 2000 to 2006 a total of 52 CPUE samples of spider wasps (Hymenoptera: Pompilidae) were collected in the mosaic landscape of the Kampinos National Park (Poland), which is a UNESCO Biosphere Reserve. The hypothesis tested was that both pompilid species richness and abundance is positively associated with spatial heterogeneity. The patterns in spider wasp assemblages were identified using a Kohonen artificial neural network (i.e., self-organizing map). The highest numbers and greatest species richness of pompilids were recorded at sites in open habitats, especially those located on dry soils that are the preferred nesting sites of ground nesting (endogeic) spider wasps. However, pompilid distribution depended not only on the character of a sampling site, but also its location in a mosaic of habitats. The highest values of pompilid abundance and species richness were also recorded at sites surrounded by several different habitats. Both parameters were lower at sites in more homogenous areas, where there were fewer habitats within the flight ranges of spider wasps. A group of three “cultural species” (Agenioideus cinctellus, A. sericeus and Auplopus carbonarius) was identified that is significantly associated with wooden buildings. The results of this study are thus consistent with the concept that habitat heterogeneity enhances faunal diversity, as each type of habitat, including anthropogenic ones, potentially contributes to a wider range of available resources., Kartarzyna Szczepko, Andrzej Kruk, Maciej Bartos., and Obsahuje seznam literatury