Combining multiple models has been recently exploited for the development of reliable neural networks. This paper introduces a structure-adaptive self-organizing map (SOM) which can adapt the structure as well as the weights, and presents a method to improve the performance by combining the multiple maps. The structure-adaptive SOM places the nodes of prototype vectors into the pattern space properly so as to make the decision boundaries as close to the class boundaries as possible. In order to show the performance of the proposed method, experiments with the unconstrained handwritten digit database of Concordia University in Canada have been conducted.
Bibliographical noteFunding Information:
This work was supported in part by a grant from the Brain Science Research Center with the brain research program of the Ministry of Science and Technology in Korea.
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Theoretical Computer Science
- Computer Science Applications
- Information Systems and Management
- Artificial Intelligence