DocumentCode :
3251670
Title :
Proposal of fully complex-valued neural networks
Author :
Hirose, Akira
Author_Institution :
Res. Center for Adv. Sci. & Technol., Tokyo Univ., Japan
Volume :
4
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
152
Abstract :
A novel neural network that processes input vectors and attractors fully in complex space is proposed. Real and imaginary data are treated consistently with an equivalent significance. This network can be applied for ill-posed problems concerning realistic physical objects, e.g., brain current estimations using highly sensitive magnetometers and sonic field reconstructions. A kind of local minima existing in conventional neural networks can be extinguished in this system because the proposed neural network deals with the data in a doubled dimension. Conventional systems using only real values do so in a degenerate space. The dynamics of the fully complex-valued neural networks are presented and the features are analyzed
Keywords :
neural nets; attractors; brain current estimations; complex space; complex-valued neural networks; doubled dimension; dynamics; ill-posed problems; local minima; magnetometers; sonic field reconstructions; Associative memory; Biological neural networks; Current measurement; Image reconstruction; Neural networks; Neurons; Proposals; SQUID magnetometers; Space technology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227274
Filename :
227274
Link To Document :
بازگشت