A new phasor model of neural networks is proposed in which the state of each neuron possibly takes the value at the origin as well as on the unit circle. A stability property of equilibria is studied in association with the energy landscape. It is shown that a simple condition guarantees an equilibrium to be asymptotically stable.
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
Teruyuki MIYAJIMA, Fumihito BAISHO, Kazuo YAMANAKA, Kazuhiko NAKAMURA, Masahiro AGU, "A Phasor Model with Resting States" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 2, pp. 299-301, February 2000, doi: .
Abstract: A new phasor model of neural networks is proposed in which the state of each neuron possibly takes the value at the origin as well as on the unit circle. A stability property of equilibria is studied in association with the energy landscape. It is shown that a simple condition guarantees an equilibrium to be asymptotically stable.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_2_299/_p
Copy
@ARTICLE{e83-d_2_299,
author={Teruyuki MIYAJIMA, Fumihito BAISHO, Kazuo YAMANAKA, Kazuhiko NAKAMURA, Masahiro AGU, },
journal={IEICE TRANSACTIONS on Information},
title={A Phasor Model with Resting States},
year={2000},
volume={E83-D},
number={2},
pages={299-301},
abstract={A new phasor model of neural networks is proposed in which the state of each neuron possibly takes the value at the origin as well as on the unit circle. A stability property of equilibria is studied in association with the energy landscape. It is shown that a simple condition guarantees an equilibrium to be asymptotically stable.},
keywords={},
doi={},
ISSN={},
month={February},}
Copy
TY - JOUR
TI - A Phasor Model with Resting States
T2 - IEICE TRANSACTIONS on Information
SP - 299
EP - 301
AU - Teruyuki MIYAJIMA
AU - Fumihito BAISHO
AU - Kazuo YAMANAKA
AU - Kazuhiko NAKAMURA
AU - Masahiro AGU
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2000
AB - A new phasor model of neural networks is proposed in which the state of each neuron possibly takes the value at the origin as well as on the unit circle. A stability property of equilibria is studied in association with the energy landscape. It is shown that a simple condition guarantees an equilibrium to be asymptotically stable.
ER -