Designing translation invariant operations via neural network training

The main objective of this work is to develop an analytical method for designing translation invariant operators via neural network training. A new neural network architecture, called modular morphological neural network (MMNN), is defined using a fundamental result of minimal representations for tr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	de Sousa, R.P., de Carvalho, J.M., de Assis, F.M., Pessoa, L.F.C.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Algorithm design and analysis Design methodology Genetic algorithms Gray-scale Image edge detection Mathematics Morphology Neural networks Pattern recognition Statistics
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!