Abrupt variations of attractors caused by argumental discreteness in non-Hermitian complex-valued neural networks are reported. When we apply the complex-valued associative memories to dynamical processing, the weighting matrices are constructed as non-Hermitian in general so that they have motive force to the signal vectors. It is observed that competitions between argumental rotation force and noise-suppression ability of associative memories lead to trajectory distortions and abrupt variations of the attractors.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Akira HIROSE, "Abrupt Variations of Attractors Caused by Argumental Discreteness in Non-Hermitian Associative Memories" in IEICE TRANSACTIONS on Fundamentals,
vol. E76-A, no. 5, pp. 777-779, May 1993, doi: .
Abstract: Abrupt variations of attractors caused by argumental discreteness in non-Hermitian complex-valued neural networks are reported. When we apply the complex-valued associative memories to dynamical processing, the weighting matrices are constructed as non-Hermitian in general so that they have motive force to the signal vectors. It is observed that competitions between argumental rotation force and noise-suppression ability of associative memories lead to trajectory distortions and abrupt variations of the attractors.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e76-a_5_777/_p
Copy
@ARTICLE{e76-a_5_777,
author={Akira HIROSE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Abrupt Variations of Attractors Caused by Argumental Discreteness in Non-Hermitian Associative Memories},
year={1993},
volume={E76-A},
number={5},
pages={777-779},
abstract={Abrupt variations of attractors caused by argumental discreteness in non-Hermitian complex-valued neural networks are reported. When we apply the complex-valued associative memories to dynamical processing, the weighting matrices are constructed as non-Hermitian in general so that they have motive force to the signal vectors. It is observed that competitions between argumental rotation force and noise-suppression ability of associative memories lead to trajectory distortions and abrupt variations of the attractors.},
keywords={},
doi={},
ISSN={},
month={May},}
Copy
TY - JOUR
TI - Abrupt Variations of Attractors Caused by Argumental Discreteness in Non-Hermitian Associative Memories
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 777
EP - 779
AU - Akira HIROSE
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 1993
AB - Abrupt variations of attractors caused by argumental discreteness in non-Hermitian complex-valued neural networks are reported. When we apply the complex-valued associative memories to dynamical processing, the weighting matrices are constructed as non-Hermitian in general so that they have motive force to the signal vectors. It is observed that competitions between argumental rotation force and noise-suppression ability of associative memories lead to trajectory distortions and abrupt variations of the attractors.
ER -