Title :
Self-organizing multilayer semantic maps
Author :
Ichiki, Hiroyuki ; Hagiwara, Masafumi ; Nakagawa, Masao
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Abstract :
Self-organizing multilayer semantic maps are proposed. Three-layer models are simulated using two examples. Since the proposed networks are multilayer type, then can do higher-level information processing compared with the conventional minimal two-layer semantic maps. The computer simulation results indicate the effectiveness of the proposed maps. The maps can do hierarchical self-classification both in a self-organizing symbol map and in a role-based semantic map
Keywords :
digital simulation; neural nets; self-organising storage; computer simulation; hierarchical self-classification; information processing; role-based semantic map; self organising multilayer semantic maps, three layer models; self-organizing symbol map; Biological information theory; Biological neural networks; Computational modeling; Computer simulation; Encoding; Humans; Information processing; Nonhomogeneous media; Organisms; Psychology;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155203
