| 单层反馈PLN网络的识别复杂性 |
| |
| 引用本文： | 张钹 张铃. 单层反馈PLN网络的识别复杂性[J]. 计算机学报, 1993, 16(5): 321-326 |
| |
| 作者姓名： | 张钹 张铃 |
| |
| 作者单位： | 清华大学计算机科学与技术系，安庆师范学院数学系 北京 100084，安庆 246011 |
| |
| 摘 要： | 本文讨论将单层反馈PLN(概率逻辑神经元模型)网络当作联想记忆网络时,其识别的复杂性问题,即其平均识别速度与网络规模之间的数量关系,我们得到的主要结论是,设单层反馈PLN网络N的规模为m,则其识别计算量是m的指数函数,给出识别计算量是m多项式的必要条件。
|
| 关 键 词： | PLN网络 单层反馈 识别 复杂性 |
THE COMPLEXITY OF RECOGNITION IN THESINGLE-LAYERED PLN NETWORKWITH FEEDBACK CONNECTIONS |
| |
| Zhang BoDept,of Computer Science and Technology,Tsinghua University,Beijing Zhang Ling Deft,of Mathematics,Anqing Teachers' College,Anqing. THE COMPLEXITY OF RECOGNITION IN THESINGLE-LAYERED PLN NETWORKWITH FEEDBACK CONNECTIONS[J]. Chinese Journal of Computers, 1993, 16(5): 321-326 |
| |
| Authors: | Zhang BoDept of Computer Science Technology Tsinghua University Beijing Zhang Ling Deft of Mathematics Anqing Teachers' College Anqing |
| |
| Affiliation: | Zhang BoDept,of Computer Science and Technology,Tsinghua University,Beijing 100084Zhang Ling Deft,of Mathematics,Anqing Teachers' College,Anqing 246011 |
| |
| Abstract: | Regarding a single-layered PLN network with feedback connections as an associative memory network,the complexity of recognition is discussed.The main result is : if the size of the network N is m,then the complexity of recognition is an exponential function of m.The necessary condition in which the complexity is polynomial is given. |
| |
| Keywords: | PLN network stable state associative memory network Markov chain transition matrix the complexity of recognition. |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
