The self-organizing map algorithm has been used successfully in document organization. We now propose using the same algorithm for document retrieval. Moreover, we test the performance of the self-organizing map by replacing the linear Least Mean Squares adaptation rule with the marginal median. We present two implementations of the latter variant of the self-organizing map by either quantifyin...

A large number of registration techniques rely on manually selected landmark points. A system based on neural principles has been developed to automatically extract landmark types and positional information from magnetic resonance images. A single self-organising map is used to develop the features (landmark types) so that the final landmarks represent statistically significant contour sections...

While feature selection is very difficult for high dimensional, unstructured data such as face image, it may be much easier to do if the data can be faithfully transformed into lower dimensional space. In this paper, a new method is proposed to transform the high dimensional face images into low-dimensional SOM topological space, and then identify important local features of face images for fac...

In this article we present an approach for the interactive retrieval of objects from databases that is based on the similarity of the objects. The considered objects are grouped based on their similarity to realise interactive associative search and visual exploration of the database. This enables a user to navigate through similar objects. If a textual description is available, the navigation,...

Different classes of communication network topologies and their representation in the form of adjacency matrix and its eigenvalues are presented. A self-organizing feature map neural network is used to map different classes of communication network topological patterns. The neural network simulation results are reported.

We present a method for clustering the speakers from unlabeled and unsegmented conversation (with known number of speakers), when no a priori knowledge about the identity of the participants is given. Each speaker was modeled by a self-organizing map (SOM). The SOMs were randomly initiated. An iterative algorithm allows the data move from one model to another and adjust the SOMs. The restrictio...

A new training and recall method for self-organizing maps (SOM) is developed by comparison of SOM to the human information processing system. As neurons and cortical columns do not change their activity instantly, it is increased or decreased in a smooth way. This fact is introduced in SOM-neurons. In a same way, recognition of objects is supposed to be a task of analysing complete sets of feat...

Previously, we proposed an approach for corporate decision making with self-organizing patent maps labeled by technical terms and AHP. First, we extracted keywords by text mining to transform patent documents into feature vectors of the companies. Second, we inputted the feature matrix of technical terms and company names into self-organizing maps to create patent maps labeled by the technical ...