Title :
Dynamical intelligent network based on group representation theory
Author :
Fujisaka, Hasato ; Akita, Maki ; Morisue, M.
Author_Institution :
Fac. of Inf. Sci., Hiroshima City Univ., Japan
fDate :
6/23/1905 12:00:00 AM
Abstract :
This paper presents a method and an example of constructing dynamical intelligent networks with a symmetric coupling structure. The presented network is inspired by a hypothesis on the activity of the neurons connected by a hexagonal lattice structure in the cerebral cortex. In the network information is represented by spatiotemporal patterns in terms of the network activity. The formation of the spatio-temporal pattern, the association of the spatial pattern with the temporal behavior is based on group representation theory. A model of attention is constructed based on the networks and its computer simulation is shown
Keywords :
analogue processing circuits; group theory; neural nets; phase locked loops; PLL; cerebral cortex; dynamical intelligent networks; group representation theory; hexagonal lattice structure; network activity; spatio-temporal patterns; symmetric coupling structure; Artificial neural networks; Biological system modeling; Brain modeling; Cerebral cortex; Computer simulation; Intelligent networks; Lattices; Neurons; Oscillators; Spatiotemporal phenomena;
Conference_Titel :
Electronics, Circuits and Systems, 2001. ICECS 2001. The 8th IEEE International Conference on
Print_ISBN :
0-7803-7057-0
DOI :
10.1109/ICECS.2001.957676
