Improving neural networks through modularization
This thesis explores and investigates various possibilities to modularize neural net-works to improve its performance and enhance its capability for pattern classifica-tion and function approximation. We have developed a novel Class-Modularized Neural Network, which utilizes one subnetwork for each...
Saved in:
主要作者: | Ong, Thian Hock. |
---|---|
其他作者: | Chen, Yan Qiu |
格式: | Theses and Dissertations |
出版: |
2008
|
主題: | |
在線閱讀: | http://hdl.handle.net/10356/5011 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
相似書籍
-
Neural networks for ATM traffic control
由: Ng, Hock Soon.
出版: (2008) -
Efficient learning through biological neural network-Hebbian learning
由: Zhou, Yanpeng
出版: (2022) -
Size estimation through neural network for a common class of web-based systems
由: Wang, Di
出版: (2008) -
Efficient learning in neural networks
由: Yin, Tong.
出版: (2009) -
Neural networks in complex field
由: Li, Mingbin
出版: (2011)