會議論文
| 學年 | 93 |
|---|---|
| 學期 | 1 |
| 發表日期 | 2004-12-18 |
| 作品名稱 | Novel Dynamic Structure Neural Network for Optical Character Recognition |
| 作品名稱（其他語言） | |
| 著者 | Hsiao, Ying-Tung; Chien, Cheng-Chih; Chuang, Cheng-Long |
| 作品所屬單位 | 淡江大學電機工程學系 |
| 出版者 | N.Y.: IEEE (Institute of Electrical and Electronic Engineers) |
| 會議名稱 | The 4th IEEE International Symposium on Signal Processing and Information Technology |
| 會議地點 | Rome, Italy |
| 摘要 | This paper presents a novel dynamic structure neural network (DSNN) and a learning algorithm for training DSNN. The performance of a neural network system depends on several factors. In that, the architecture of a neural network plays an important role. The objective of the developing DSNN is to avoid trial-and-error process for designing a neural network system. The architecture of DSNN consists of a three-dimensional set of neurons with input/output nodes and connection weights. Designers can define the maximum connection number of each neuron. Moreover, designers can manually deploy neurons in a virtual 3D space, or randomly generate the system structure by the proposed learning algorithm. This work also develops an automatic restructuring algorithm integrated in the proposed learning algorithm to improve the system performance. Due to the novel dynamic structure of DSNN and the restructuring algorithm, the design of DSNN is fast and convenient. Furthermore, DSNN is implemented in C++ with man-machine interactive procedures and tested on many cases with very promising results. |
| 關鍵字 | |
| 語言 | en |
| 收錄於 | |
| 會議性質 | 國際 |
| 校內研討會地點 | |
| 研討會時間 | 20041218~20041221 |
| 通訊作者 | Cheng-Long Chuang |
| 國別 | ITA |
| 公開徵稿 | Y |
| 出版型式 | |
| 出處 | Signal Processing and Information Technology, 2004. Proceedings of the Fourth IEEE International Symposium on, pp.357-360 |
| 相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/70501 ) |