| 应用新的聚类技术加速B－P网络的收敛过程 |
| |
| 引用本文： | 陈武凡,鲁贤庆,陈建军,张浩生.应用新的聚类技术加速B－P网络的收敛过程[J].南方医科大学学报,1994(3). |
| |
| 作者姓名： | 陈武凡 鲁贤庆 陈建军 张浩生 |
| |
| 作者单位： | Chen Wufan，Lu
Xiangqing，Chen Jianjun，et al Department of Biomedical Engineering |
| |
| 摘 要： | Ｂ－Ｐ网络在模式识别技术中识别效果好，应用较广泛，但通过模式样本直接对网络权训练，收敛过程太慢。就模式识别的软、硬分类问题，提出基于新的聚类方法条件下进行网络权的训练，收敛速度较快，可收事半功倍之效。
|
| 关 键 词： | 神经网络 人工智能 模式识别 样本 权 计算机 |
Accelerating the convergence of B-P network by using a new cluster technique |
| |
| Chen Wufan,Lu
Xiangqing,Chen Jianjun,et al.Accelerating the convergence of B-P network by using a new cluster technique[J].Journal of Southern Medical University,1994(3). |
| |
| Authors: | Chen Wufan Lu
Xiangqing Chen Jianjun |
| |
| Institution: | Chen Wufan,Lu
Xiangqing,Chen Jianjun,et al Department of Biomedical Engineering |
| |
| Abstract: | -P network has very
high efficiency of recognition and has been widely used. But usually ,the pro-cess of the
convergence is very slow if the weights of the network are directly trained through the
patternsamples. In this paper,a procedure based on a new cluster technique is proposed to train
the weights ofthe network for hard or soft classification problems of pattern recognition,and the
convergence process isaccelerated. |
| |
| Keywords: | neural network artifical intelligence pattern recognition sample weight computer |
| 本文献已被 CNKI 等数据库收录！ |
