Recent developments in the area of neural networks produced models capable of dealing with structured data. Here, we propose the first fully unsupervised model, namely an extension of traditional self-organizing maps (SOMs), for the processing of labeled directed acyclic graphs (DAGs). The extension is obtained by using the unfolding procedure adopted in recurrent and recursive neural networks,...

As digital music and sound collections increase in size there has been a lot of work in developing novel interfaces for browsing them. Many of these interfaces rely on automatic content analysis techniques to create representations that reflect similarities between the music pieces or sounds in the collection. Representations in 3D have the potential to convey more information but can be diffic...

In the statistical approach for self-organizing maps (SOMs), learning is regarded as an estimation algorithm for a gaussian mixture model with a gaussian smoothing prior on the centroid parameters. The values of the hyperparameters and the topological structure are selected on the basis of a statistical principle. However, since the component selection probabilities are fixed to a common value,...

We describe a novel approach to anchoring symbols in the sensory data of a hybrid autonomous system. Using an autonomous mobile robot as a test platform we show how an Isomap can be used to detect and properly classify time-series of sensory data. In the past, similar approaches have used self-organizing maps (SOMs) for this purpose. Isomap can be regarded as an improved technique for generatin...

The paper presents scheme for doing Domain Adaptation for multiple domains simultaneously. The proposed method segments a large corpus into various parts using self-organizing maps (SOMs). After a SOM is drawn over the documents, an agglomerative clustering algorithm determines how many clusters the text collection comprised. This means that the clustering process is unsupervised, although choi...

This paper presents some interesting results obtained by the algorithm by Bauer, Der and Hermann (BDH) [1] for magnification control in Self-Organizing Maps. Magnification control in SOMs refers to the modification of the relationship between the probability density functions of the input samples and their prototypes (SOM weights). The above mentioned algorithm enables explicit control of the m...

A topology-selection method for self-organizing maps (SOMs) based on empirical Bayesian inference is presented. This method is natural extension of the hyperparameter-selection method presented earlier, in which the SOM algorithm is regarded as an estimation algorithm for a Gaussian mixture model with a Gaussian smoothing prior on the centroid parameters, and optimal hyperparameters are obtaine...

The Radon transform in combination with self-organizing maps is used to build the rotation invariant systems for categorization of visual objects. The first system has one SOM per the Radon transform direction. The outputs from these directional SOMs that represent positions of the winners and related post-synaptic activities, form the input to the final categorizing SOM. Such a network deliver...

Electroencephalogram (EEG) is an important clinical tool for diagnosing, monitoring, and managing neurological disorders related to epilepsy. Neural networks provide intriguing possibilities for the analysis of the EEG. In this paper we propose a neural network based system to detect epileptic activity. The system comprises of three main components: feature extraction, feature quantization and ...

Many conventional digital library systems offer access to their collections only via full text or meta-data search, or by browsingaccess via a hierarchy of categories. With the increasing amount of digital content available, alternative methods to access the content seem necessary. The SOMLib system, which is based on using Self-Organizing Maps (SOMs), has been used to automatically organize do...