In the domain of classification tasks, artificial neural nets (ANNs) are prominent data mining methods. Paradigms like learning vector quantization (LVQ) and probabilistic neural net (PNN) are suitable classifiers. In this paper, new approaches of evolutionary optimized LVQs and PNNs are proposed. Their classification accuracy is compared with results of standard PNN and LVQ. The complex real-w...

Our text-independent speaker verification system, referred to as WCL-1, is based on Probabilistic Neural Networks (PNNs). WCL-1 has a modular structure with a distinct PNN for each enrolled user. A gender-dependent reference model, representing the world of possible impostors, is employed for counterbalancing the scores produced by the users’ models. The year 2004 WCL-1 system is basically a re...

The impact of two different impostor modelling techniques on the performance of a Probabilistic Neural Networks (PNNs)-based text-independent speaker verification system is studied. Depending on the technique used for background codebook construction, two versions of the system are obtained: with one universal background codebook, common to all authorized speakers, and with an individual speake...

Large water distribution systems can be highly vulnerable to penetration of contaminant factors caused by different means including deliberate contamination injections. As contaminants quickly spread into a water distribution network, rapid characterization of the pollution source has a high measure of importance for early warning assessment and disaster management. In this paper, a methodology...

Many Text Classification (TC) algorithms have been proposed for Arabic TC. Polynomial Neural Networks (PNNs) were used recently in English TC, and have proved to be competitive to the state of the art text classifiers in this field. Lately, they were proposed for classifying Arabic documents. In this research paper, an experimental study that directly compares PNNs against five famous classific...

Aggrecan, a chondroitin sulfate (CS) proteoglycan, forms lattice-like extracellular matrix structures called perineuronal nets (PNNs). Neocortical PNNs primarily ensheath parvalbumin-expressing inhibitory neurons (parvalbumin, PV cells) late in brain development. Emerging evidence indicates that PNNs promote the maturation of PV cells by enhancing the incorporation of homeobox protein Otx2 and ...

Perineuronal nets (PNNs) are extracellular matrix structures surrounding cortical neuronal cell bodies and proximal dendrites and are involved in the control of brain plasticity and the closure of critical periods. Expression of the link protein Crtl1/Hapln1 in neurons has recently been identified as the key event triggering the formation of PNNs. Here we show that the genetic attenuation of PN...

This paper presents an easy to use constructive training algorithm for Probabilis tic Neural Networks a special type of Radial Basis Function Networks In contrast to other algorithms prede nition of the network topology is not required The pro posed algorithm introduces new hidden units whenever necessary and adjusts the shape of already existing units individually to minimize the risk of miscl...

Neural networks have been used prominently in several machine learning and statistics applications. In general, the underlying optimization of neural networks is non-convex which makes their performance analysis challenging. In this paper, we take a novel approach to this problem by asking whether one can constrain neural network weights to make its optimization landscape have good theoretical ...