|
|||||
|
|
| 基于约束区域的BSB联想记忆模型 | |
| 引用本文： | 陶卿,方廷健,孙德敏.基于约束区域的BSB联想记忆模型[J].计算机学报,2000,23(3):266-271. |
| 作者姓名： | 陶卿 方廷健 孙德敏 |
| 作者单位： | 1. 中国科学技术大学自动化系,合肥,230027;中国人民解放军炮兵学院作战指挥实验中心,合肥,230031 2. 中国科学院合肥智能机械研究所,合肥,230031 3. 中国科学技术大学自动化系,合肥,230027 |
| 摘 要： | 提出一种根据联想记忆点设计基于约束区域的ＢＳＢ（Ｂｒａｉｎ－Ｓｔａｔｅ－ｉｎｍ－ａ－Ｂｏｘ）神经网络模型，它保证了渐近稳定的平衡点集与样本点集相同，不渐近稳定的平衡点恰为实际的拒识状态，并且吸引域分布合理，从而将ＥＳＢ完善为理想的联想记忆器。 |
| 关 键 词： | 神经网络 联想记忆 约束区域 BSB模型 |
| 修稿时间： | 1999-05-31 |
The BSB Neural Network Based on the Constraint Domain for Associative Memory |
|
| TAO Qing,FANG Ting-Jian,SUN De-Min.The BSB Neural Network Based on the Constraint Domain for Associative Memory[J].Chinese Journal of Computers,2000,23(3):266-271. | |
| Authors: | TAO Qing FANG Ting-Jian SUN De-Min |
| Abstract: | This paper presents a neural network based on the constraint domain according to prototype patterns. It guarantees that the set of prototype patterns is the same as the set of asymptotically stable equilibrium points,an equilibrium point which is not asymptotically stable is just the state that can not be recognized. Furthermore, the basin of attraction of each desired memory pattern is distributed reasonably (in the Hamming distance sense). The proposed network improves BSB as an idea model for associative memory. |
| Keywords: | neural networks associative memory constraint domain equilibrium points basin of attraction projection operator |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |