Title :
Self-organized learning of 3 dimensions
Author :
Szepesvári, Cs ; Lörincz, A.
Author_Institution :
Inst. of Isotopes, Hungarian Acad. of Sci., Budapest, Hungary
fDate :
27 Jun-2 Jul 1994
Abstract :
The geometric learning capabilities of a competitive neural network are studied. It is shown that the appropriate selection of a neural activity function enables the learning of the 3D geometry of a world, from two of the 2D projections of 3D extended objects
Keywords :
Hebbian learning; self-organising feature maps; solid modelling; spatial reasoning; 2D projections; 3D extended objects; 3D geometry; competitive neural network; geometric learning capabilities; neural activity function selection; self-organized learning; Artificial neural networks; Geometry; Isotopes; Neural networks; Neurofeedback; Neurons; Organizing; Software algorithms; Spatial filters; Wire;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374256
