Unsupervised global optimization: applications on classification of handwritten digits and visual evoked potentials

The authors discuss the optical recognition of handwritten unconnected numerals and visual evoked potential (VEP) classification using two neural network learning paradigms. The first is an unsupervised approach, trained by the combinatorial optimization routine ALOPEX, while the second method uses...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE International Conference on Systems, Man and Cybernetics, 1992 s. 381 - 386 vol.1
Hlavní autoři: Micheli-Tzanakou, E., Dasey, T.J.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 1992
Témata:
Artificial neural networks
Backpropagation algorithms
Biomedical engineering
Character recognition
Feature extraction
Medical diagnostic imaging
Multiple sclerosis
Neural networks
Pattern recognition
System testing
ISBN:0780307208, 9780780307209
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The authors discuss the optical recognition of handwritten unconnected numerals and visual evoked potential (VEP) classification using two neural network learning paradigms. The first is an unsupervised approach, trained by the combinatorial optimization routine ALOPEX, while the second method uses the backpropagation algorithm. The unsupervised ALOPEX trained system classifies 1000 training digits to an accuracy of 86.3%, and 500 generalizing characters 86.0% accurately. This compares to 99.8% and 93% for a network trained with the supervised backpropagation algorithm. The system was used to cluster the VEPs of normal and multiple sclerosis (MS) subjects. The method demonstrates two distinct groups of subjects, which when histogrammed illustrate that they largely correspond to the MS and control subject groups. A suitable threshold can be chosen so that the recognizer chooses no false negatives.< >
ISBN:0780307208
9780780307209
DOI:10.1109/ICSMC.1992.271745