| 图样间联想光学神经网络模型存贮分析及两层异联想识别模型的构造 |
| |
| 引用本文： | 许锐,李志能,黄达诠,毕岗.图样间联想光学神经网络模型存贮分析及两层异联想识别模型的构造[J].光子学报,2000,29(12):1091-1095. |
| |
| 作者姓名： | 许锐 李志能 黄达诠 毕岗 |
| |
| 作者单位： | 浙江大学信息与电子工程系电子信息技术研究所 310027 |
| |
| 基金项目： | 浙江省自然科学基金资助项目 |
| |
| 摘 要： | 本文详细讨论了图样间联想网络的最大存贮容量,给出了实现图样间异联想的两个充分条件.在此基础上,利用改进的图样间异联想算法构造了两层异联想模型(THA)用于图样识别,网络判辨率与恢复率较图样间自联想识别均有很大提高;且其互连权矩阵更加简单稀疏并可平面化,光学实现更为简便.
|
| 关 键 词： | 光学神经网络 图样间联想 异联想 存贮容量 图样恢复 |
| 收稿时间： | 2000-03-31 |
| 修稿时间： | 2000-03-28 |
ANALYSIS ON THE STORAGE CAPACITY OF IPA MODEL AND THE CONSTRUCTION OF A TWO LAYER HETERO ASSOCIATION OPTICAL NEURAL NETWORK MODEL |
| |
| Xu Rui,Li Zhineng,Huang Daquan,Bi Gang.ANALYSIS ON THE STORAGE CAPACITY OF IPA MODEL AND THE CONSTRUCTION OF A TWO LAYER HETERO ASSOCIATION OPTICAL NEURAL NETWORK MODEL[J].Acta Photonica Sinica,2000,29(12):1091-1095. |
| |
| Authors: | Xu Rui Li Zhineng Huang Daquan Bi Gang |
| |
| Institution: | Institute of Electronic Information Technology, Department of Information & Electronic Engineering, Zhejiang University, Yuquan, Hangzhou 310027, China |
| |
| Abstract: | The utmost storage capacity of the interpattern association (IPA) neural network is discussed in this paper,and two sufficient terms of realizing interpattern heteroassociation are pointed out as a further step.Next a two layer heteroassociation model (THA) is proposed by using the modified IHA algorithm,and the recognition of 10 digital numbers by THA has shown much improved performances compared with the IPA model in both identifying and retrieving patterns.Moreover,THA owns sparser weight matrixes (IWM) with 1 D interconnections,which brings more convenience to optical implementation. |
| |
| Keywords: | Optical neural network Interpattern association Heteroassociation Storage capacity Pattern retrievap |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《光子学报》浏览原始摘要信息 |
| 点击此处可从《光子学报》下载免费的PDF全文 |
