A Clustering Based Method to Stipulate the Number of Hidden Neurons of mlp Neural Networks: Applications in Pattern Recognition
oleh: M.R. Silvestre, S.M. Oikawa, F.H.T. Vieira, L.L. Ling
| Format: | Article |
|---|---|
| Diterbitkan: | Sociedade Brasileira de Matemática Aplicada e Computacional 2008-06-01 |
Deskripsi
In this paper, we propose an algorithm to obtain the number of necessary hidden neurons of single-hidden-layer feed forward networks (SLFNs) for different pattern recognition application tasks. Our approach is based on clustering analysis of the data in each class. We show by simulations that the proposed approach requires less computation CPU time and error rates as well as a smaller number of neurons than other methods.