Title :
Hybrid neural network based on models of multilayer perceptron and adaptive resonance theory
Author_Institution :
Novosibirsk State Tech. Univ., Russia
fDate :
26 June-2 July 2005
Abstract :
The model of the hybrid neural network is considered. This model consists of model ART-2 for clusterization and perceptron for preprocessing of images. The perceptron provides invariant recognition of objects. This model can be used in mobile robots for recognition of new objects or scenes in sight the robot during his movement.
Keywords :
ART neural nets; image recognition; mobile robots; multilayer perceptrons; object recognition; robot vision; ART-2 model; adaptive resonance theory; clusterization; hybrid neural network; image preprocessing; mobile robots; multilayer perceptron; object recognition; robot sight; scene recognition; Clustering algorithms; Image converters; Image recognition; Mobile robots; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Pattern recognition; Resonance;
Conference_Titel :
Science and Technology, 2005. KORUS 2005. Proceedings. The 9th Russian-Korean International Symposium on
Print_ISBN :
0-7803-8943-3
DOI :
10.1109/KORUS.2005.1507794
