Self-Organizing Neural Networks by Construction and Pruning

Jong-Seok LEE  Hajoon LEE  Jae-Young KIM  Dongkyung NAM  Cheol Hoon PARK  

IEICE TRANSACTIONS on Information and Systems   Vol.E87-D   No.11   pp.2489-2498
Publication Date: 2004/11/01
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Biocybernetics, Neurocomputing
self-organizing neural network,  construction,  pruning,  impact factor,  pool of candidates,  

Full Text: PDF>>
Buy this Article

Feedforward neural networks have been successfully developed and applied in many areas because of their universal approximation capability. However, there still remains the problem of determining a suitable network structure for the given task. In this paper, we propose a novel self-organizing neural network which automatically adjusts its structure according to the task. Utilizing both the constructive and the pruning procedures, the proposed algorithm finds a near-optimal network which is compact and shows good generalization performance. One of its important features is reliability, which means the randomness of neural networks is effectively reduced. The resultant networks can have suitable numbers of hidden neurons and hidden layers according to the complexity of the given task. The simulation results for the well-known function regression problems show that our method successfully organizes near-optimal networks.