Journal of the Korean Institute of Telematics and Electronics C (전자공학회논문지C)
- Volume 34C Issue 7
- /
- Pages.70-81
- /
- 1997
- /
- 1226-5853(pISSN)
Hybrid multiple component neural netwrok design and learning by efficient pattern partitioning method
효과적인 패턴분할 방법에 의한 하이브리드 다중 컴포넌트 신경망 설계 및 학습
Abstract
In this paper, we propose HMCNN(hybrid multiple component neural networks) that enhance performance of MCNN by adapting new pattern partitioning algorithm which can cluster many input patterns efficiently. Added neural network performs similar learning procedure that of kohonen network. But it dynamically determine it's number of output neurons using algorithms that decide self-organized number of clusters and patterns in a cluster. The proposed network can effectively be applied to problems of large data as well as huge networks size. As a sresutl, proposed pattern partitioning network can enhance performance results and solve weakness of MCNN like generalization capability. In addition, we can get more fast speed by performing parallel learning than that of other supervised learning networks.
Keywords