A performance comparison of two self-organizing networks, the Kohonen Feature Map and the recently proposed Growing Cell Structures is made. For this purpose several performance criteria for self-organizing networks are proposed and motivated. The models are tested with three example problems of increasing difficulty. The Kohonen Feature Map demonstrates slightly superior results only for the s...

Self-organizing maps, SOMs, are a data visualization technique developed to reduce the dimensions of data through the use of self-organizing neural networks. However, as the original input manifold can be complicated with an inherent dimension larger than that of the feature map, the dimension reduction in SOM can be too drastic, generating a folded feature map. In order to eliminate this pheno...

Obtaining semantic or functional word categories from data in an unsupervised manner is a problem motivated both from the linguistic point of view and from that of construing language models for various language processing tasks. In this work, we use the Self-Organizing Map algorithm to visualize and cluster common Finnish verbs based on their immediate morphological contexts. Based on a data s...

Monitoring of chemical processes is becoming increasingly difficult as a result of growing complexity and larger scale of operation. In this paper, Kohonen self-organizing map s (SOM) is used to monitor the operation of a lab-scale distillation column and to identify process states. SOM projects high -dimensional data to a lower two dimensional grid maps while preserving the metric relations of...

In this paper we describe a novel use of a multi-layer Kohonen self-organizing feature map (MLKSFM) for spoken language identification (LID). A normalized, segment-based input feature vector is used in order to maintain the temporal information of speech signal. The LID is performed by using different system configurations of the MLKSFM. Compared with a baseline PPRLM system, our novel system i...

A self-organizing neural network for sequence classification called SARDNET is described and analyzed experimentally. SARDNET extends the Kohonen Feature Map architecture with activation retention and decay in order to create unique distributed response patterns for different sequences. SARDNET yields extremely dense yet descriptive representations of sequential input in very few training itera...

The explosive growth of digital image collections on the Web sites is calling for an efficient and intelligent method of browsing, searching, and retrieving images. In this article, an artificial neural network (ANN)-based approach is proposed to explore a promising solution to the Web image retrieval (IR). Compared with other image retrieval methods, this new approach has the following charact...