This paper introduces a new fuzzy representation for isolated character description. This representation maps a character from its original sequence of 2D coordinates into a fuzzy vector space that can thereafter serve as input to any artificial neural network classifier. Recognition experiments on isolated digits extracted from the UNIPEN database are then conducted to evaluate the performance...

The paper describes the model, implementation and experimental evaluation of a distributed Kohonen Neural Network application (Kohonen Application). The aim of this research is to empirically verify the suitability and the performance of a distributed application based on mobile objects and, in perspective, intelligent agents. This research is aims to provide distribution features in decision s...

Important and relevant information is expected to be encoded in local structural elements of proteins. An unsupervised learning algorithm (Kohonen algorithm) was applied to the representation and unbiased classification of local backbone structures contained in a set of proteins. Training yielded a two-dimensional Kohonen feature map with 100 different structural motifs including certain helica...

in the science of operation research and decision theory, selection is the most important process. selection is a process that studies multiple qualitative and quantitative criteria, related to the science of management, which are mostly incompatible with each other. the multi criteria selection of a renewable energy portfolio is one of the main issues considered in multi criteria literature. i...

The ight control system of migratory locusts is able to adapt its steering behaviour to varying conditions in its motor system or in the animals' immediate environment. A connectionist simulation model based on a Kohonen network extended by multi-dimensional output signals was employed to reproduce the adaptive control performances. For the output signals of the network a trial and error learni...

We designed and built a high-capacity neural network based on volume holographic interconnections in a photorefractive crystal. We used this system to implement a Kohonen topological map. We describe and justify our optical setup and present some experimental results of self-organization in the learning database.

An algorithm of evolving self-organizing map (ESOM) is proposed as a dynamic version of the Kohonen self-organizing map, where network structure is evolved in an on-line adaptive mode. Experiments have been carried out on some benchmark data sets as well as on macroeconomic data. Results show that ESOM is a good tool for clustering, data analysis, and visualisation.

A multi-model neural network computer has been designed and realized. A compute intensive application using the Kohonen self-organizing map, in the eld of power system monitoring , has been ported onto the neu-ral machine. The system is described and its performance is evaluated and discussed.

In this paper we describe a learning technique for reactive path-planning and guidance of autonomous robots using a Kohonen self-organizing neural network. The intended application is mineral exploration or agricultural monitoring using simple lowcost robots which do not contain a complete stored map of the environment, and may have unreliable sensor information. The network learns based on a s...