IEICE TRANSACTIONS on Information
Dynamic Constructive Fault Tolerant Algorithm for Feedforward Neural Networks
Summary :
In this paper, a dynamic constructive algorithm for fault tolerant feedforward neural network, called DCFTA, is proposed. The algorithm starts with a network with single hidden neuron, and a new hidden unit is added dynamically to the network whenever it fails to converge. Before inserting the new hidden neuron into the network, only the weights connecting the new hidden neuron to the other neurons are trained (i. e. , updated) until there is no significant reduction of the output error. To generate a fault tolerant network, the relevance of each synaptic weight is estimated in each cycle, and only the weights which have their relevance less than a specified threshold are updated in that cycle. The loss of a connections between neurons (which are equivalent to stuck-at-0 faults) are assumed. The simulation results indicate that the network constructed by DCFTA has a significant fault tolerance ability.
- Publication
- IEICE TRANSACTIONS on Information Vol.E81-D No.1 pp.115-123
- Publication Date
- 1998/01/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Category
- Bio-Cybernetics and 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
Nait Charif HAMMADI, Toshiaki OHMAMEUDA, Keiichi KANEKO, Hideo ITO, "Dynamic Constructive Fault Tolerant Algorithm for Feedforward Neural Networks" in IEICE TRANSACTIONS on Information,
vol. E81-D, no. 1, pp. 115-123, January 1998, doi: .
Abstract: In this paper, a dynamic constructive algorithm for fault tolerant feedforward neural network, called DCFTA, is proposed. The algorithm starts with a network with single hidden neuron, and a new hidden unit is added dynamically to the network whenever it fails to converge. Before inserting the new hidden neuron into the network, only the weights connecting the new hidden neuron to the other neurons are trained (i. e. , updated) until there is no significant reduction of the output error. To generate a fault tolerant network, the relevance of each synaptic weight is estimated in each cycle, and only the weights which have their relevance less than a specified threshold are updated in that cycle. The loss of a connections between neurons (which are equivalent to stuck-at-0 faults) are assumed. The simulation results indicate that the network constructed by DCFTA has a significant fault tolerance ability.
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_1_115/_p
Copy
@ARTICLE{e81-d_1_115,
author={Nait Charif HAMMADI, Toshiaki OHMAMEUDA, Keiichi KANEKO, Hideo ITO, },
journal={IEICE TRANSACTIONS on Information},
title={Dynamic Constructive Fault Tolerant Algorithm for Feedforward Neural Networks},
year={1998},
volume={E81-D},
number={1},
pages={115-123},
abstract={In this paper, a dynamic constructive algorithm for fault tolerant feedforward neural network, called DCFTA, is proposed. The algorithm starts with a network with single hidden neuron, and a new hidden unit is added dynamically to the network whenever it fails to converge. Before inserting the new hidden neuron into the network, only the weights connecting the new hidden neuron to the other neurons are trained (i. e. , updated) until there is no significant reduction of the output error. To generate a fault tolerant network, the relevance of each synaptic weight is estimated in each cycle, and only the weights which have their relevance less than a specified threshold are updated in that cycle. The loss of a connections between neurons (which are equivalent to stuck-at-0 faults) are assumed. The simulation results indicate that the network constructed by DCFTA has a significant fault tolerance ability.},
keywords={},
doi={},
ISSN={},
month={January},}
Copy
TY - JOUR
TI - Dynamic Constructive Fault Tolerant Algorithm for Feedforward Neural Networks
T2 - IEICE TRANSACTIONS on Information
SP - 115
EP - 123
AU - Nait Charif HAMMADI
AU - Toshiaki OHMAMEUDA
AU - Keiichi KANEKO
AU - Hideo ITO
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 1998
AB - In this paper, a dynamic constructive algorithm for fault tolerant feedforward neural network, called DCFTA, is proposed. The algorithm starts with a network with single hidden neuron, and a new hidden unit is added dynamically to the network whenever it fails to converge. Before inserting the new hidden neuron into the network, only the weights connecting the new hidden neuron to the other neurons are trained (i. e. , updated) until there is no significant reduction of the output error. To generate a fault tolerant network, the relevance of each synaptic weight is estimated in each cycle, and only the weights which have their relevance less than a specified threshold are updated in that cycle. The loss of a connections between neurons (which are equivalent to stuck-at-0 faults) are assumed. The simulation results indicate that the network constructed by DCFTA has a significant fault tolerance ability.
ER -
English
