| 快速单像素多目独立成分设计 |
| |
| 引用本文： | 佘堃,蒲红梅,郑方伟,周明天. 快速单像素多目独立成分设计[J]. 电子科技大学学报(社会科学版), 2008, 0(3) |
| |
| 作者姓名： | 佘堃 蒲红梅 郑方伟 周明天 |
| |
| 作者单位： | 电子科技大学计算机科学与工程学院;重庆通信学院第四系;电子科技大学计算机科学与工程学院 成都610054四川省计算机软件重点实验室成都;重庆沙坪坝区;成都610054四川省计算机软件重点实验室成都; |
| |
| 基金项目： | 四川省学术带头人后备人才基金(Y02001010601011) |
| |
| 摘 要： | 分析了LCNN的约束项的物理意义,认为约束项λ是有监督学习的加速度,使得整个算法无论是学习矩阵还是独立成分的求解效率都可达到O(n)。针对不同的λ和源信号、观测信号对的不同特性,提出了4种快速LCNN算法,分析了静态图像独立成分分析模型,建立了单像素内的独立模型,并总结了其优势。
|
| 关 键 词： | Helmholtz自由能 独立成分分析(ICA) Lagrange约束神经网络 单像素内独立成分模型 |
Fast Design of Independent Component Based on Single Pixel under Multisensing |
| |
| SHE Kun,,PU Hong-mei,ZHENG Fang-wei,, ZHOU Ming-tian. Fast Design of Independent Component Based on Single Pixel under Multisensing[J]. Journal of University of Electronic Science and Technology of China(Social Sciences Edition), 2008, 0(3) |
| |
| Authors: | SHE Kun PU Hong-mei ZHENG Fang-wei ZHOU Ming-tian |
| |
| Affiliation: | SHE Kun1,2,PU Hong-mei3,ZHENG Fang-wei1,, ZHOU Ming-tian1,2 (1. School of Computer Science , Engineering,University of Electronic Science , Technology of China Chengdu 610054,2. Sichuan KeyLab on Computer Software Chengdu 610066,3. 4th Department,Chongqing Communication College Shapingba Chongqing 400035 ) |
| |
| Abstract: | The traditional independent component analysis is based on statistics mean of all aposteriori data and dismissed geometry. The classical lagrange constraint neural network (LCNN) employs Helmholtz free energy to unify supervised and unsupervised learning, and uses aprior and multi-sensing to solve independent components in one pixel, whose geometrical grain reached single pixel. The operations among pixels can be completely run parallelly. However, the constraints of classical LCNN bring ill-conditional mat... |
| |
| Keywords: | Helmholtz free energy independent component lagrange constraint neural network sub-pixel independent component model |
| 本文献已被 CNKI 等数据库收录！ |
|
