題名: | Learning generative models of handwritten digit images |
作者: | Wu, Jiann-Ming Lin, Zheng-Han |
關鍵字: | neural networks generative models cortical maps elastic net Potts model self-organization unsupervised leaning handwritten digits |
期刊名/會議名稱: | 2002 ICS會議 |
摘要: | This work explores generative models of handwritten digit images using natural elastic net. The analysis aims to discober global features as well as distributed local features of handwritten digits. These features are expected to form a significant basis for discriminant analsis of handwritten digits and relate analysis of handwritten characters that are beyond digits but possess similar features. |
日期: | 2006-10-24T01:00:42Z |
分類: | 2002年 ICS 國際計算機會議 |
文件中的檔案:
檔案 | 描述 | 大小 | 格式 | |
---|---|---|---|---|
ce07ics002002000346.PDF | 381.54 kB | Adobe PDF | 檢視/開啟 |
在 DSpace 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。