In this paper, we present a novel and efficient approach for automatic design of Artificial Neural Networks (ANNs) by evolving to the optimal network configuration(s) within an ar...
E. Alper Yildirim, Ince Turker, Moncef Gabbouj, Se...
—Structural learning with forgetting is an established method of using Laplace regularization to generate skeletal artificial neural networks. In this paper we develop a continu...
The self-organising map (SOM) has been successfully employed as a nonparametric method for dimensionality reduction and data visualisation. However, for visualisation the SOM requ...
This paper presents a new approach for shape description and invariant recognition by geometric-normalization implemented by neural networks. The neural system consists of a shape...
In this paper we introduce novel geometric concepts, namely category regions, in the original framework of Fuzzy-ART (FA) and FuzzyARTMAP (FAM). The definitions of these regions a...
Georgios C. Anagnostopoulos, Michael Georgiopoulos