A SOM Association Network
In this paper, we propose a self-organizing map association (SOMA) network which associates a perfect information from a part of the information. The processes of the SOMA network are divided into a learning mode and an association mode. In the learning mode, the similar perfect informations are represented by a few units on the competitive layer. In the association mode, when the information, whose parts are lost, is applied to the SOMA network, the lost part is associated. The performance of the SOMA network is evaluated by applying to the association of the data used in the orthodontics.
KeywordsWeight Vector Input Vector Input Layer Perfect Information Learning Mode
Unable to display preview. Download preview PDF.
- Legan HL, Burstone CJ, “Soft tissue cephalometric analysis for orthognathic surgery”, J Oral Sung, Vol. 38, pp. 744-751, 1980.Google Scholar