Learning Algorithms Which Make Multilayer Neural Networks Multiple-Weight-and-Neuron-Fault Tolerant
Summary :
Two simple but useful methods, called the deep learning methods, for making multilayer neural networks tolerant to multiple link-weight and neuron-output faults, are proposed. The methods make the output errors in learning phase smaller than those in practical use. The abilities of fault-tolerance of the multilayer neural networks in practical use, are analyzed in the relationship between the output errors in learning phase and in practical use. The analytical result shows that the multilayer neural networks have complete (100%) fault-tolerance to multiple weight-and-neuron faults in practical use. The simulation results concerning the rate of successful learnings, the ability of fault-tolerance, and the learning time, are also shown.
- Publication
- IEICE TRANSACTIONS on Information Vol.E91-D No.4 pp.1168-1175
- Publication Date
- 2008/04/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e91-d.4.1168
- Type of Manuscript
- PAPER
- Category
- Biocybernetics, Neurocomputing
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
Tadayoshi HORITA, Itsuo TAKANAMI, Masatoshi MORI, "Learning Algorithms Which Make Multilayer Neural Networks Multiple-Weight-and-Neuron-Fault Tolerant" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 4, pp. 1168-1175, April 2008, doi: 10.1093/ietisy/e91-d.4.1168.
Abstract: Two simple but useful methods, called the deep learning methods, for making multilayer neural networks tolerant to multiple link-weight and neuron-output faults, are proposed. The methods make the output errors in learning phase smaller than those in practical use. The abilities of fault-tolerance of the multilayer neural networks in practical use, are analyzed in the relationship between the output errors in learning phase and in practical use. The analytical result shows that the multilayer neural networks have complete (100%) fault-tolerance to multiple weight-and-neuron faults in practical use. The simulation results concerning the rate of successful learnings, the ability of fault-tolerance, and the learning time, are also shown.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.4.1168/_p
Copy
@ARTICLE{e91-d_4_1168,
author={Tadayoshi HORITA, Itsuo TAKANAMI, Masatoshi MORI, },
journal={IEICE TRANSACTIONS on Information},
title={Learning Algorithms Which Make Multilayer Neural Networks Multiple-Weight-and-Neuron-Fault Tolerant},
year={2008},
volume={E91-D},
number={4},
pages={1168-1175},
abstract={Two simple but useful methods, called the deep learning methods, for making multilayer neural networks tolerant to multiple link-weight and neuron-output faults, are proposed. The methods make the output errors in learning phase smaller than those in practical use. The abilities of fault-tolerance of the multilayer neural networks in practical use, are analyzed in the relationship between the output errors in learning phase and in practical use. The analytical result shows that the multilayer neural networks have complete (100%) fault-tolerance to multiple weight-and-neuron faults in practical use. The simulation results concerning the rate of successful learnings, the ability of fault-tolerance, and the learning time, are also shown.},
keywords={},
doi={10.1093/ietisy/e91-d.4.1168},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Learning Algorithms Which Make Multilayer Neural Networks Multiple-Weight-and-Neuron-Fault Tolerant
T2 - IEICE TRANSACTIONS on Information
SP - 1168
EP - 1175
AU - Tadayoshi HORITA
AU - Itsuo TAKANAMI
AU - Masatoshi MORI
PY - 2008
DO - 10.1093/ietisy/e91-d.4.1168
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2008
AB - Two simple but useful methods, called the deep learning methods, for making multilayer neural networks tolerant to multiple link-weight and neuron-output faults, are proposed. The methods make the output errors in learning phase smaller than those in practical use. The abilities of fault-tolerance of the multilayer neural networks in practical use, are analyzed in the relationship between the output errors in learning phase and in practical use. The analytical result shows that the multilayer neural networks have complete (100%) fault-tolerance to multiple weight-and-neuron faults in practical use. The simulation results concerning the rate of successful learnings, the ability of fault-tolerance, and the learning time, are also shown.
ER -
English
