It has already been shown how Artificial Neural Networks (ANNs) can be incorporated into probabilistic models. In this paper we review some of the approaches which have been prop...
Many machine learning algorithms can be formulated as the minimization of a training criterion which involves (1) \training errors" on each training example and (2) some hype...
The choice of transfer functions may strongly influence complexity and performance of neural networks used in classification and approximation tasks. A taxonomy of activation an...
Any performance evaluation of broadband networks requires modeling of the actual network traffic. Since multimedia services and especially MPEG coded video streams are expected to...
Anastasios D. Doulamis, Nikolaos D. Doulamis, Stef...
A self-organizing neural network for learning and recall of complex temporal sequences is proposed. we consider a single sequence with repeated items, or several sequences with a c...
The aim of this work is to propose and discuss a technique which allows for classifying the defects found in metallic components on the basis of a non-destructive Remote-Field Edd...
S. Barcherini, L. Cipiccia, M. Maggi, Simone Fiori...
In this paper we present the growing hierarchical self-organizing map. This dynamically growing neural network model evolves into a hierarchical structure according to the requirem...