Abstract
In this paper, a new approach is proposed to reduce the complexity of radial basis function (RBF) networks. This approach starts with an enough number of hidden nodes and reduces the number of nodes in the course of learning. The algorithm can be employed in the problems where only the performance index of the network output is given, as well as in the supervised training problems where the desired output values are available. Also, it is applicable to either of classification problems and function approximation problems.
| Original language | English |
|---|---|
| Pages | 1308-1312 |
| Number of pages | 5 |
| Publication status | Published - Dec 1 1999 |
| Event | International Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA Duration: Jul 10 1999 → Jul 16 1999 |
Other
| Other | International Joint Conference on Neural Networks (IJCNN'99) |
|---|---|
| City | Washington, DC, USA |
| Period | 7/10/99 → 7/16/99 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Artificial Intelligence
Cite this
Size-reducing RBF networks. / Murata, Junichi; Itoh, Shinji; Hirasawa, Kotaro.
1999. 1308-1312 Paper presented at International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, .Research output: Contribution to conference › Paper
}
TY - CONF
T1 - Size-reducing RBF networks
AU - Murata, Junichi
AU - Itoh, Shinji
AU - Hirasawa, Kotaro
PY - 1999/12/1
Y1 - 1999/12/1
N2 - In this paper, a new approach is proposed to reduce the complexity of radial basis function (RBF) networks. This approach starts with an enough number of hidden nodes and reduces the number of nodes in the course of learning. The algorithm can be employed in the problems where only the performance index of the network output is given, as well as in the supervised training problems where the desired output values are available. Also, it is applicable to either of classification problems and function approximation problems.
AB - In this paper, a new approach is proposed to reduce the complexity of radial basis function (RBF) networks. This approach starts with an enough number of hidden nodes and reduces the number of nodes in the course of learning. The algorithm can be employed in the problems where only the performance index of the network output is given, as well as in the supervised training problems where the desired output values are available. Also, it is applicable to either of classification problems and function approximation problems.
UR - http://www.scopus.com/inward/record.url?scp=0033325255&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033325255&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0033325255
SP - 1308
EP - 1312
ER -