| 引用本文: | 陈松灿,刘 征.具有内连接的指数多值双向联想记忆模型[J].控制理论与应用,2002,19(1):65~67.[点击复制] |
| CHEN Songcan,LIU Zheng.Exponential Bidirectional Associative Memory Model with Intraconnection[J].Control Theory and Technology,2002,19(1):65~67.[点击复制] |
|
| 具有内连接的指数多值双向联想记忆模型 |
| Exponential Bidirectional Associative Memory Model with Intraconnection |
| 摘要点击 2758 全文点击 1354 投稿时间：2000-03-13 修订日期：2000-09-11 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2002.1.013 |
| 2002,19(1):65-67 |
| 中文关键词 (多值)双向联想记忆 指数 神经网络 稳定性 内连接 |
| 英文关键词 multi_valued) bidirectional associative memory exponent neural networks stability intraconnection |
| 基金项目 国家自然科学基金(69701004); 教育部青年骨干教师资助计划资助项目 |
|
| 中文摘要 |
| C_CWang的多值指数双向联想记忆模型 (MVeBAM)是一种高存储容量的联想神经网络. 本文在MVe BAM的基础上通过引入自相关项 (或内连接 )提出了一个新的具有内连接的多值指数双向联想记忆模型, 推广了MVeBAM. 通过定义简单的能量函数证明了其在同、异步方式下的稳定性, 从而保证了所学模式对成为被推广的MVeBAM(EMVeBAM)的稳定点. 最后, 计算机模拟证实了EMVeBAM比MVeBAM具有更高的存储容量和更好的纠错性能. |
| 英文摘要 |
| C_C Wang's multi_valued exponential bidirectional associative memory model (MVeBAM) is a neural network with higher storage capacity. In this paper, based on the MVeBAM, we propose a new multi_valued exponential bidirectional associative memory model with intraconnection (EMVeBAM) by adding an auto_correlation term (or an intraconnection) to the exponents, extending the MVeBAM. The stability of the proposed model is proven in synchronous and asynchronous update modes with a defined energy function, which ensures that the learnt patterns become stable points of the EMeBAM. Finally, the computer simulation results verify that the EMVeBAM has higher storage capacity and better error_correcting capability than those of MVeBAM. |