Abstract
How to determine the appropriate or optimal activation function in the neural networks for a specific learning samples remains open. In this paper the cascade-correlation algorithm which is an efficient constructive algorithm is used after implementation of some kinds of clustering algorithms to produce a modular network structure as a surrogate of activation node functions in the radial basis function (RBF) networks. In this way great improvement on the convergence rate of training algorithms and better approximation are achieved. Simulations with the two-spiral data sets proved the above assertion.
| Original language | English |
|---|---|
| Title of host publication | IECON Proceedings (Industrial Electronics Conference) |
| Pages | 1177-1182 |
| Number of pages | 6 |
| Volume | 2 |
| Publication status | Published - 2000 |
| Externally published | Yes |
| Event | 26th Annual Conference of the IEEE Electronics Society IECON 2000 - Nagoya Duration: 2000 Oct 22 → 2000 Oct 28 |
Other
| Other | 26th Annual Conference of the IEEE Electronics Society IECON 2000 |
|---|---|
| City | Nagoya |
| Period | 00/10/22 → 00/10/28 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
Cite this
Wan, W., Hirasawa, K., Murata, J., Jin, C., & Furuzuki, T. (2000). Determination of the appropriate node function of NNs by using the cascade-correlation algorithms. In IECON Proceedings (Industrial Electronics Conference) (Vol. 2, pp. 1177-1182)