In this paper, we describe an implementation of analog neural network system with on-line learning capability. A learning rule using the simultaneous perturbation is adopted. Compared with usage of the ordinary back-propagation method, we can easily implement the simultaneous perturbation learning rule. The neural system can monitor weight values and an error value. The exclusive OR problem and a simple function problem are shown.
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
Yutaka MAEDA, Toshiyuki KUSUHASHI, "An Analog Neural Network System with Learning Capability Using Simultaneous Perturbation" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 12, pp. 1627-1633, December 1999, doi: .
Abstract: In this paper, we describe an implementation of analog neural network system with on-line learning capability. A learning rule using the simultaneous perturbation is adopted. Compared with usage of the ordinary back-propagation method, we can easily implement the simultaneous perturbation learning rule. The neural system can monitor weight values and an error value. The exclusive OR problem and a simple function problem are shown.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_12_1627/_p
Copy
@ARTICLE{e82-d_12_1627,
author={Yutaka MAEDA, Toshiyuki KUSUHASHI, },
journal={IEICE TRANSACTIONS on Information},
title={An Analog Neural Network System with Learning Capability Using Simultaneous Perturbation},
year={1999},
volume={E82-D},
number={12},
pages={1627-1633},
abstract={In this paper, we describe an implementation of analog neural network system with on-line learning capability. A learning rule using the simultaneous perturbation is adopted. Compared with usage of the ordinary back-propagation method, we can easily implement the simultaneous perturbation learning rule. The neural system can monitor weight values and an error value. The exclusive OR problem and a simple function problem are shown.},
keywords={},
doi={},
ISSN={},
month={December},}
Copy
TY - JOUR
TI - An Analog Neural Network System with Learning Capability Using Simultaneous Perturbation
T2 - IEICE TRANSACTIONS on Information
SP - 1627
EP - 1633
AU - Yutaka MAEDA
AU - Toshiyuki KUSUHASHI
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 1999
AB - In this paper, we describe an implementation of analog neural network system with on-line learning capability. A learning rule using the simultaneous perturbation is adopted. Compared with usage of the ordinary back-propagation method, we can easily implement the simultaneous perturbation learning rule. The neural system can monitor weight values and an error value. The exclusive OR problem and a simple function problem are shown.
ER -