Multi-Layer Perceptron with Pulse Glial Chain

Chihiro IKUTA; Yoko UWATE; Yoshifumi NISHIO; Guoan YANG

doi:10.1587/transfun.E99.A.742

Multi-Layer Perceptron with Pulse Glial Chain

Chihiro IKUTA, Yoko UWATE, Yoshifumi NISHIO, Guoan YANG

Full Text Views

0

Cite this

Summary :

Glial cells include several types of cells such as astrocytes, and oligodendrocytes apart from the neurons in the brain. In particular, astrocytes are known to be important in higher brain function and are therefore sometimes simply called glial cells. An astrocyte can transmit signals to other astrocytes and neurons using ion concentrations. Thus, we expect that the functions of an astrocyte can be applied to an artificial neural network. In this study, we propose a multi-layer perceptron (MLP) with a pulse glial chain. The proposed MLP contains glia (astrocytes) in a hidden layer. The glia are connected to neurons and are excited by the outputs of the neurons. The excited glia generate pulses that affect the excitation thresholds of the neurons and their neighboring glia. The glial network provides a type of positional relationship between the neurons in the hidden layer, which can enhance the performance of MLP learning. We confirm through computer simulations that the proposed MLP has better learning performance than a conventional MLP.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E99-A No.3 pp.742-755

Publication Date: 2016/03/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E99.A.742

Type of Manuscript: PAPER

Category: Neural Networks and Bioengineering

Authors

Chihiro IKUTA
  Tokushima University
Yoko UWATE
  Tokushima University
Yoshifumi NISHIO
  Tokushima University
Guoan YANG
  Xi'an Jiaotong University

Keyword

multi-layer perceptron, glial chain, classification

Cite this

Copy

Chihiro IKUTA, Yoko UWATE, Yoshifumi NISHIO, Guoan YANG, "Multi-Layer Perceptron with Pulse Glial Chain" in IEICE TRANSACTIONS on Fundamentals, vol. E99-A, no. 3, pp. 742-755, March 2016, doi: 10.1587/transfun.E99.A.742.
Abstract: Glial cells include several types of cells such as astrocytes, and oligodendrocytes apart from the neurons in the brain. In particular, astrocytes are known to be important in higher brain function and are therefore sometimes simply called glial cells. An astrocyte can transmit signals to other astrocytes and neurons using ion concentrations. Thus, we expect that the functions of an astrocyte can be applied to an artificial neural network. In this study, we propose a multi-layer perceptron (MLP) with a pulse glial chain. The proposed MLP contains glia (astrocytes) in a hidden layer. The glia are connected to neurons and are excited by the outputs of the neurons. The excited glia generate pulses that affect the excitation thresholds of the neurons and their neighboring glia. The glial network provides a type of positional relationship between the neurons in the hidden layer, which can enhance the performance of MLP learning. We confirm through computer simulations that the proposed MLP has better learning performance than a conventional MLP.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E99.A.742/_p

Copy

@ARTICLE{e99-a_3_742,
author={Chihiro IKUTA, Yoko UWATE, Yoshifumi NISHIO, Guoan YANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Multi-Layer Perceptron with Pulse Glial Chain},
year={2016},
volume={E99-A},
number={3},
pages={742-755},
abstract={Glial cells include several types of cells such as astrocytes, and oligodendrocytes apart from the neurons in the brain. In particular, astrocytes are known to be important in higher brain function and are therefore sometimes simply called glial cells. An astrocyte can transmit signals to other astrocytes and neurons using ion concentrations. Thus, we expect that the functions of an astrocyte can be applied to an artificial neural network. In this study, we propose a multi-layer perceptron (MLP) with a pulse glial chain. The proposed MLP contains glia (astrocytes) in a hidden layer. The glia are connected to neurons and are excited by the outputs of the neurons. The excited glia generate pulses that affect the excitation thresholds of the neurons and their neighboring glia. The glial network provides a type of positional relationship between the neurons in the hidden layer, which can enhance the performance of MLP learning. We confirm through computer simulations that the proposed MLP has better learning performance than a conventional MLP.},
keywords={},
doi={10.1587/transfun.E99.A.742},
ISSN={1745-1337},
month={March},}

Copy

TY - JOUR
TI - Multi-Layer Perceptron with Pulse Glial Chain
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 742
EP - 755
AU - Chihiro IKUTA
AU - Yoko UWATE
AU - Yoshifumi NISHIO
AU - Guoan YANG
PY - 2016
DO - 10.1587/transfun.E99.A.742
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E99-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2016
AB - Glial cells include several types of cells such as astrocytes, and oligodendrocytes apart from the neurons in the brain. In particular, astrocytes are known to be important in higher brain function and are therefore sometimes simply called glial cells. An astrocyte can transmit signals to other astrocytes and neurons using ion concentrations. Thus, we expect that the functions of an astrocyte can be applied to an artificial neural network. In this study, we propose a multi-layer perceptron (MLP) with a pulse glial chain. The proposed MLP contains glia (astrocytes) in a hidden layer. The glia are connected to neurons and are excited by the outputs of the neurons. The excited glia generate pulses that affect the excitation thresholds of the neurons and their neighboring glia. The glial network provides a type of positional relationship between the neurons in the hidden layer, which can enhance the performance of MLP learning. We confirm through computer simulations that the proposed MLP has better learning performance than a conventional MLP.
ER -