Online learning with ensembles.
Online learning with ensembles.
复制标题
与合奏团在线学习。
DOI：
10.1103/physreve.62.1448
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
R. Urbanczik
中科院分区：
文献类型：
--
作者：
R. Urbanczik
分析了由初始条件选择随机化的学生群体进行的监督在线学习。对于感知器学习规则的情况下，渐近相同的改进相比，一个单一的学生的表现，在吉布斯学习的集成的泛化误差。然而，对于更优化的学习规则，使用集成不会产生任何改进。这是通过证明对于任何学习规则f，存在变换f来解释的，使得使用f的单个学生具有与f个学生的集合相同的泛化行为。
Supervised online learning with an ensemble of students randomized by the choice of initial conditions is analyzed. For the case of the perceptron learning rule, asymptotically the same improvement in the generalization error of the ensemble compared to the performance of a single student is found as in Gibbs learning. For more optimized learning rules, however, using an ensemble yields no improvement. This is explained by showing that for any learning rule f a transform f exists, such that a single student using f has the same generalization behavior as an ensemble of f students.