We derive the eigenvalue constraint for a neural network with three degrees of freedom. The result implies that the neural network needs a neuron with variable output function to generate chaos. It is also shown that the neuron with the special characteristics can be constructed by ordinary neurons.
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
Hideo MATSUDA, Akihiko UCHIYAMA, "A Neural Network Model for Generating Intermittent Chaos" in IEICE TRANSACTIONS on Fundamentals,
vol. E76-A, no. 9, pp. 1544-1547, September 1993, doi: .
Abstract: We derive the eigenvalue constraint for a neural network with three degrees of freedom. The result implies that the neural network needs a neuron with variable output function to generate chaos. It is also shown that the neuron with the special characteristics can be constructed by ordinary neurons.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e76-a_9_1544/_p
Copy
@ARTICLE{e76-a_9_1544,
author={Hideo MATSUDA, Akihiko UCHIYAMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Neural Network Model for Generating Intermittent Chaos},
year={1993},
volume={E76-A},
number={9},
pages={1544-1547},
abstract={We derive the eigenvalue constraint for a neural network with three degrees of freedom. The result implies that the neural network needs a neuron with variable output function to generate chaos. It is also shown that the neuron with the special characteristics can be constructed by ordinary neurons.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - A Neural Network Model for Generating Intermittent Chaos
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1544
EP - 1547
AU - Hideo MATSUDA
AU - Akihiko UCHIYAMA
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 1993
AB - We derive the eigenvalue constraint for a neural network with three degrees of freedom. The result implies that the neural network needs a neuron with variable output function to generate chaos. It is also shown that the neuron with the special characteristics can be constructed by ordinary neurons.
ER -