Abstract
For a supervised learning method, the quality of the training data or the training supervisor is very important in generating reliable neural networks. However, for real world problems, it is not always easy to obtain high quality training data sets. In this research, we propose a learning method for a neural network ensemble model that can be trained with an imperfect training data set, which is a data set containing erroneous training samples. With a competitive training mechanism, the ensemble is able to exclude erroneous samples from the training process, thus generating a reliable neural network. Through the experiment, we show that the proposed model is able to tolerate the existence of erroneous training samples in generating a reliable neural network. The ability of the neural network to tolerate the existence of erroneous samples in the training data lessens the costly task of analyzing and arranging the training data, thus increasing the usability of the neural networks for real world problems.
| Original language | English |
|---|---|
| Pages (from-to) | 353-363 |
| Number of pages | 11 |
| Journal | Applied Soft Computing Journal |
| Volume | 7 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 2007 Jan |
Fingerprint
Keywords
- Competitive learning
- Imperfect supervisor
- Neural network ensemble
- Temperature
ASJC Scopus subject areas
- Software
- Computer Science Applications
- Artificial Intelligence
Cite this
Learning from imperfect data. / Hartono, Pitoyo; Hashimoto, Shuji.
In: Applied Soft Computing Journal, Vol. 7, No. 1, 01.2007, p. 353-363.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Learning from imperfect data
AU - Hartono, Pitoyo
AU - Hashimoto, Shuji
PY - 2007/1
Y1 - 2007/1
N2 - For a supervised learning method, the quality of the training data or the training supervisor is very important in generating reliable neural networks. However, for real world problems, it is not always easy to obtain high quality training data sets. In this research, we propose a learning method for a neural network ensemble model that can be trained with an imperfect training data set, which is a data set containing erroneous training samples. With a competitive training mechanism, the ensemble is able to exclude erroneous samples from the training process, thus generating a reliable neural network. Through the experiment, we show that the proposed model is able to tolerate the existence of erroneous training samples in generating a reliable neural network. The ability of the neural network to tolerate the existence of erroneous samples in the training data lessens the costly task of analyzing and arranging the training data, thus increasing the usability of the neural networks for real world problems.
AB - For a supervised learning method, the quality of the training data or the training supervisor is very important in generating reliable neural networks. However, for real world problems, it is not always easy to obtain high quality training data sets. In this research, we propose a learning method for a neural network ensemble model that can be trained with an imperfect training data set, which is a data set containing erroneous training samples. With a competitive training mechanism, the ensemble is able to exclude erroneous samples from the training process, thus generating a reliable neural network. Through the experiment, we show that the proposed model is able to tolerate the existence of erroneous training samples in generating a reliable neural network. The ability of the neural network to tolerate the existence of erroneous samples in the training data lessens the costly task of analyzing and arranging the training data, thus increasing the usability of the neural networks for real world problems.
KW - Competitive learning
KW - Imperfect supervisor
KW - Neural network ensemble
KW - Temperature
UR - http://www.scopus.com/inward/record.url?scp=33750957495&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33750957495&partnerID=8YFLogxK
U2 - 10.1016/j.asoc.2005.07.005
DO - 10.1016/j.asoc.2005.07.005
M3 - Article
AN - SCOPUS:33750957495
VL - 7
SP - 353
EP - 363
JO - Applied Soft Computing
JF - Applied Soft Computing
SN - 1568-4946
IS - 1
ER -