|
|||||
|
|
| 一种多权值神经元覆盖网络的构造方法 | |
| 引用本文： | 魏莱,徐菲菲,王守觉.一种多权值神经元覆盖网络的构造方法[J].计算机学报,2012,35(5):1031-1037. |
| 作者姓名： | 魏莱 徐菲菲 王守觉 |
| 作者单位： | 1. 上海海事大学计算机科学系 上海201305 2. 上海电力学院计算机科学与技术系 上海200090 3. 中国科学院半导体研究所神经网络实验室 北京100083 |
| 基金项目： | 上海市优秀青年教师基金，上海市教育委员会科研创新基金 |
| 摘 要： | 仿生模式识别利用多权值神经元覆盖网络构造模式类的覆盖来进行相应事物的识别.但在构造多权值神经元覆盖网络的过程中,关于构造神经元个数的确定方法没有相关讨论,即需要使用多少个神经元才能完成对模式类的覆盖.较多的神经元在精确的对模式类进行覆盖同时,也增大了网络的复杂度.文中提出了一种多权值神经元覆盖网络的构造方法.在保持神经网络对模式类的覆盖能力的基础上采用尽量少的神经元,从而能有效的降低神经网络构造代价.最后,通过实验作者验证了算法的有效性. |
| 关 键 词： | 模式识别 神经元 单纯形 覆盖 多维尺度变换 |
Constructive Algorithm of Multi-Weight Neuron Covering Networks |
|
| WEI Lai , XU Fei-Fei , WANG Shou-Jue.Constructive Algorithm of Multi-Weight Neuron Covering Networks[J].Chinese Journal of Computers,2012,35(5):1031-1037. | |
| Authors: | WEI Lai XU Fei-Fei WANG Shou-Jue |
| Affiliation: | 1)(Department of Computer Science,Shanghai Maritime University,Shanghai 201305) 2)(Department of Computer Science and Technology,Shanghai University of Electric Power,Shanghai 200090) 3)(Laboratory of Artificial Neural Networks,Institute of Semiconductor,Chinese Academy of Science,Beijing 100083) |
| Abstract: | Biomimetic Pattern Recognition theory uses multi-weight neuron covering networks to perform recognition tasks.However,there are few discussions on the constructive methods of multi-weight neuron covering networks,namely how many neurons are needed to fulfill the covering of a data set.A large number of neurons can cover the data set precisely,but it will make the network be more complicated.In this paper,we propose a constructive algorithm for multi-weight neuron covering networks.The algorithm can construct a covering network with least neurons and maintain the covering ability of the networks simultaneously.The experiments show the efficiency of the proposed algorithm. |
| Keywords: | pattern recognition neuron simplex covering multidimensional scaling |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |