| 简单Perceptron学习算法的收敛性 |
| |
| 引用本文： | 冯建峰.简单Perceptron学习算法的收敛性[J].北京大学学报(自然科学版),1995,31(1):20-27. |
| |
| 作者姓名： | 冯建峰 |
| |
| 作者单位： | 北京大学概率统计系，北京，100871 |
| |
| 摘 要： | 当输入是无穷集或区域时，通过构造一个上鞅，本文证明了简单Perceptron学习算法的收敛性。
|
| 关 键 词： | 简单Perceptron 上鞅 线性可分 |
| 收稿时间： | 1994-07-24 |
A Discussion of the Learning in a Simple Perceptron |
| |
| FENG Jianfeng.A Discussion of the Learning in a Simple Perceptron[J].Acta Scientiarum Naturalium Universitatis Pekinensis,1995,31(1):20-27. |
| |
| Authors: | FENG Jianfeng |
| |
| Institution: | Dept. of Probability and Statistics, Peking University, Beijing, 100871 |
| |
| Abstract: | We extend the convergence of the simple perceptron learning rule to the case that the set of inputs is infinity or a region. When the set of inputs is linearly separable, we prove that a simple perceptron always improves its performance. As the set of the inputs is 'strong' linearly separable, then within finite time the connections among units converge to a limit which separates the inputs. The convergence rate is also estimated. |
| |
| Keywords: | simple perceptron supermartingale linearly separable |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《北京大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《北京大学学报(自然科学版)》下载免费的PDF全文 |
