-
摘要: 定义并估计了假设空间的统计量复杂性. 据此可以找到一个基数性不超过假设空间的VC (Vapnik-Chervonenkis)维多项式级的线性经验泛函集, 利用该线性经验泛函集可以构造以所需的任意精度逼近假设空间中的任一函数的学习算法. 同时给出了随机生成这些泛函的方法.
-
关键词:
- 统计量复杂性 /
- L-范数 /
- VC维 /
- Glivenko-Cantelli类
Abstract: The concept and the estimates of statistic complexity are given in this paper. We show that for a function class with a polynomial rate of the VC dimension, one can find a set of linear empirical functionals of polynomial size in the dimension that are sufficient for constructing a learning algorithm which can approximate any function in the class. At the same time, a random procedure to select these functionals is given.-
Key words:
- Statistic complexity /
- L-norm /
- VC dimension /
- Glivenko-Cantelli class
-
计量
- 文章访问数: 3200
- HTML全文浏览量: 24
- PDF下载量: 1327
- 被引次数: 0
下载:
