pollution deriving from trace elements (cd, cu, ni, pb, zn, hg, as and cr) in sediment samples(collected in 2009), belonging to rivers located in catalonia and the basque country (spain), was assessedaccording to sediment quality guidelines. sediment samples were ranked in terms of a pollution index thattakes into account the presence of multiple pollutants such as trace elements. while only ab...

Why Neural Nets? ..................................................................................................................1 What is a Neural Net?.............................................................................................................2 The Perceptron....................................................................................................................3 ...

Neural networks are a popular tool in the area of pattern recognition. However, since a very large number of neural network architectures exist, it has not been established which one is the most efficient. In this paper we compare the performance of three neural network architectures: Kohonen’s self-organizing network, probabilistic neural network, and a modified backpropagation applied to a si...

We examine how Spike-Timing-Dependent Plasticity (STDP) can strengthen recurrent excitatory connections in a network of Poisson neurons stimulated by two pools of external inputs, where only one pool has spike-time correlation. We derive conditions on the STDP and network parameters such that the network exhibits a stable activity in terms of spiking-rates and show how the evolution of the recu...

Obtaining classification systems with both good generalization performance and high recognition rates often requires careful study on methods of combining multiple classifiers. In this paper, a Kohonen self-organization neural network based combination method is proposed. The system uses the Kohonen's model to integrate the results of several neural network classifiers. The theoretical analysis...

Services for Advanced Communication Networks are described in this paper. An Artificial Neural Network will be used for the control of Network Elements, in our case a Switch. Classical sequence data processing is substituted by parallel processing. The classical switch and the switch controlled by a Kohenen Artificial Neural Network are compared. The switch has four ports and its own Quality of...

Speech recognition is a diicult problem due to the inability of current systems to cope with connected speech. Neural networks are able to learn some aspects of this task. An unsupervised learning scheme like the self-organising map can be used to both classify and order the speech sounds and provide a front end to higher level processing. A map of phonemes (phonotopic map) is used to trace tra...

Self-Organising Maps (SOM) are Artificial Neural Networks used in Pattern Recognition tasks. Their major advantage over other architectures is human readability of a model. However, they often gain poorer accuracy. Mostly used metric in SOM is the Euclidean distance, which is not the best approach to some problems. In this paper, we study an impact of the metric change on the SOM’s performance ...