For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
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
Publication Date: 2004/11/01
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>>
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.