LOWER BOUNDS ON GENERALIZATION ERRORS FOR DRIFTING RULES
LOWER BOUNDS ON GENERALIZATION ERRORS FOR DRIFTING RULES
复制标题
DOI：
10.1088/0305-4470/26/22/017
复制
发表时间：
1993-11-21
期刊：
影响因子：
--
通讯作者：
CATICHA, N
中科院分区：
文献类型：
--
作者：
KINOUCHI, O;CATICHA, N
研究了基于时间依赖规则的单层感知器泛化问题。对于随机漂移规则，得到了“单例表示”情况下泛化误差的下界。这些界限提出了一种利用误差本身知识的学习算法。由于这个误差不容易得到，因此必须通过一种自我评价机制来估计它。将近期信息纳入误差估计的能力是非常可取的。所提出的机制除了具有良好的性能外，还具有自适应的优点，即它可以根据规则的未知漂移率的变化进行调整。为了模仿所谓的威斯康辛测试，该规则的表现也会因突然变化而受到研究。
The problem of generalization by single-layer perceptrons is studied in the case of time-dependent rules. Lower bounds for the generalization errors within the 'single presentation of examples' case are obtained for randomly drifting rules. These bounds suggest a learning algorithm which uses knowledge of the error itself. Since this error is not readily available it has to be estimated through a mechanism of self-evaluation. The capacity of incorporating recency information into the error estimate is highly desirable. The mechanism proposed has the advantage, beyond good performance, of being self-adaptive, in the sense that it adjusts to changes in the unknown drift rate of the rule. The performance of the rule is also studied for sudden changes in an attempt to mimic the so-called Wisconsin test.