In this study, we propose a multi-layer perceptron with a glial network which is inspired from the features of glias in the brain. All glias in the proposed network generate independent oscillations, and the oscillations propagate through the glial network with attenuation. We apply the proposed network to the two-spiral problem. Computer simulations show that the proposed network gains a better performance than the conventional multi-layer perceptron.
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
Chihiro IKUTA, Yoko UWATE, Yoshifumi NISHIO, "Multi-Layer Perceptron with Glial Network for Solving Two-Spiral Problem" in IEICE TRANSACTIONS on Fundamentals,
vol. E94-A, no. 9, pp. 1864-1867, September 2011, doi: 10.1587/transfun.E94.A.1864.
Abstract: In this study, we propose a multi-layer perceptron with a glial network which is inspired from the features of glias in the brain. All glias in the proposed network generate independent oscillations, and the oscillations propagate through the glial network with attenuation. We apply the proposed network to the two-spiral problem. Computer simulations show that the proposed network gains a better performance than the conventional multi-layer perceptron.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E94.A.1864/_p
Copy
@ARTICLE{e94-a_9_1864,
author={Chihiro IKUTA, Yoko UWATE, Yoshifumi NISHIO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Multi-Layer Perceptron with Glial Network for Solving Two-Spiral Problem},
year={2011},
volume={E94-A},
number={9},
pages={1864-1867},
abstract={In this study, we propose a multi-layer perceptron with a glial network which is inspired from the features of glias in the brain. All glias in the proposed network generate independent oscillations, and the oscillations propagate through the glial network with attenuation. We apply the proposed network to the two-spiral problem. Computer simulations show that the proposed network gains a better performance than the conventional multi-layer perceptron.},
keywords={},
doi={10.1587/transfun.E94.A.1864},
ISSN={1745-1337},
month={September},}
Copy
TY - JOUR
TI - Multi-Layer Perceptron with Glial Network for Solving Two-Spiral Problem
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1864
EP - 1867
AU - Chihiro IKUTA
AU - Yoko UWATE
AU - Yoshifumi NISHIO
PY - 2011
DO - 10.1587/transfun.E94.A.1864
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E94-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2011
AB - In this study, we propose a multi-layer perceptron with a glial network which is inspired from the features of glias in the brain. All glias in the proposed network generate independent oscillations, and the oscillations propagate through the glial network with attenuation. We apply the proposed network to the two-spiral problem. Computer simulations show that the proposed network gains a better performance than the conventional multi-layer perceptron.
ER -