DocumentCode :
1664735
Title :
Hypergraphs: Organizing complex natural neural networks
Author :
Jain, Eakta ; Healy, Michael J. ; Saland, Linda ; Hamilton, Derek ; Allan, Andrea ; Caldwell, Kevin ; Caudell, Thomas P.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., Kanpur
fYear :
2005
Firstpage :
20
Lastpage :
26
Abstract :
Data from neuroscience research has shown that the brain can be studied as a neural network. In view of the brain´s seemingly infinite complexity, we organize the entire network into a series of sub-networks, each of whose functionalities combine to become the knowledge representation capability of the entire network. Thus, we look at the brain in terms of modules and sub-modules, at varying levels of `granularity´. Since a network can be mathematically represented as a graph, this hierarchical structure is captured through the notion of `hypergraphs´ and `hyper-matrices´. The proposed structure has been implemented on a graph specification software tool. Finally, a metaphoric visualization for the structure was proposed
Keywords :
brain; graph theory; knowledge representation; matrix algebra; neural nets; neurophysiology; complex natural neural networks; graph specification software tool; hyper-matrices; hypergraphs; knowledge representation; mathematical graph representation; metaphoric visualization; neuroscience research; Artificial neural networks; Biological neural networks; Circuit simulation; Computer networks; Data engineering; Knowledge representation; Neural networks; Neurons; Organizing; Yarn;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Sensing and Information Processing, 2005. ICISIP 2005. Third International Conference on
Conference_Location :
Bangalore
Print_ISBN :
0-7803-9588-3
Type :
conf
DOI :
10.1109/ICISIP.2005.1619407
Filename :
1619407
Link To Document :
بازگشت