IEICE TRANSACTIONS on Fundamentals
A Learning Rule of the Oscillatory Neural Networks for In-Phase Oscillation
Summary :
This peper proposes a simplified model of the well-known two-neuron neural oscillator. By eliminating one of the two positive feedback synapses in the neural oscillator, learning for the in-phase control of the oscillator is shown to be achievable via a very simple learning rule. The learning rule is devised in such a way that only the plasticity of two synaptic weights are required. We demonstrate some examples of the synchronization learning to validate the efficiency of the learning rule, and finally by illustrating the dynamics of the synchronization learning and by using computer simulation, we show the convergence behavior and the stability of the learning rule for the two-neuron simple neural oscillator.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E80-A No.9 pp.1585-1594
- Publication Date
- 1997/09/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Section on Nonlinear Theory and its Applications)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Hiroaki KUROKAWA, Chun Ying HO, Shinsaku MORI, "A Learning Rule of the Oscillatory Neural Networks for In-Phase Oscillation" in IEICE TRANSACTIONS on Fundamentals,
vol. E80-A, no. 9, pp. 1585-1594, September 1997, doi: .
Abstract: This peper proposes a simplified model of the well-known two-neuron neural oscillator. By eliminating one of the two positive feedback synapses in the neural oscillator, learning for the in-phase control of the oscillator is shown to be achievable via a very simple learning rule. The learning rule is devised in such a way that only the plasticity of two synaptic weights are required. We demonstrate some examples of the synchronization learning to validate the efficiency of the learning rule, and finally by illustrating the dynamics of the synchronization learning and by using computer simulation, we show the convergence behavior and the stability of the learning rule for the two-neuron simple neural oscillator.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e80-a_9_1585/_p
Copy
@ARTICLE{e80-a_9_1585,
author={Hiroaki KUROKAWA, Chun Ying HO, Shinsaku MORI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Learning Rule of the Oscillatory Neural Networks for In-Phase Oscillation},
year={1997},
volume={E80-A},
number={9},
pages={1585-1594},
abstract={This peper proposes a simplified model of the well-known two-neuron neural oscillator. By eliminating one of the two positive feedback synapses in the neural oscillator, learning for the in-phase control of the oscillator is shown to be achievable via a very simple learning rule. The learning rule is devised in such a way that only the plasticity of two synaptic weights are required. We demonstrate some examples of the synchronization learning to validate the efficiency of the learning rule, and finally by illustrating the dynamics of the synchronization learning and by using computer simulation, we show the convergence behavior and the stability of the learning rule for the two-neuron simple neural oscillator.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - A Learning Rule of the Oscillatory Neural Networks for In-Phase Oscillation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1585
EP - 1594
AU - Hiroaki KUROKAWA
AU - Chun Ying HO
AU - Shinsaku MORI
PY - 1997
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E80-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 1997
AB - This peper proposes a simplified model of the well-known two-neuron neural oscillator. By eliminating one of the two positive feedback synapses in the neural oscillator, learning for the in-phase control of the oscillator is shown to be achievable via a very simple learning rule. The learning rule is devised in such a way that only the plasticity of two synaptic weights are required. We demonstrate some examples of the synchronization learning to validate the efficiency of the learning rule, and finally by illustrating the dynamics of the synchronization learning and by using computer simulation, we show the convergence behavior and the stability of the learning rule for the two-neuron simple neural oscillator.
ER -
English
