 |
|
|
|
 |
 |
 |
|
 |
|
 |
|
|
| 张 铃,张 钹,殷海风.多层前向网络的交叉覆盖设计算法.软件学报,1999,10(7):737-742 |
| 多层前向网络的交叉覆盖设计算法 |
| An Alternative Covering Design Algorithm of Multi-layer Neural Networks |
| 投稿时间：1998-01-16 修订日期：1998-08-24 |
| DOI： |
| 中文关键词: 多层神经网络,设计原则,交叉覆盖算法. |
| 英文关键词:Multi-layer neural network, principle for design, alternative covering algorithm. |
| 基金项目:本文研究得到国家自然科学基金和国家863高科技项目基金资助. |
| 作者 | 单位 | | 张 铃 | 清华大学智能技术与系统国家重点实验室,北京,100084
清华大学智能技术与系统国家重点实验室,北京,100084 | | 张 钹 | 清华大学计算机科学与技术系,北京,100084
清华大学智能技术与系统国家重点实验室,北京,100084 | | 殷海风 | 安徽大学人工智能研究所,合肥,230039 |
|
| 摘要点击次数: 7556 |
| 全文下载次数: 3912 |
| 中文摘要: |
| 文章根据多层前向权、阈值神经网络的设计原则,将设计过程分成两步进行:先用尽可能少的领域将样本中的各类分隔开来,然后再用作者提出的交叉覆盖算法进行网络设计.文章给出两个很有代表性的模拟例子,一个是平面上两根螺线的分离问题,另一个是“无穷样本学习”的例子.模拟结果证明了此方法的有效性. |
| 英文摘要: |
| In this paper, the authors present a new principle for designing a sort of multi-layer weight-sum-and -threshold neural networks. The design process consists of two steps. First, each class of the given training samples is covered by using neighbor coverings as less as possible. Then a neural network is specifically designed by an approach called alternative covering algorithm. The simulation results of two representative hard classification problems are shown. One is so called “two spirals separation” problem, the other is “the learning problem of infinitetraining samples”. These simulation results are given to illustrate the effectiveness of the new method. |
|
HTML 下载PDF全文 查看/发表评论 下载PDF阅读器 |
|
|
|
|
|
|
 |
|
|
|
|
 |
|
 |
|
 |
|
