HOW INDUCTIVE INFERENCE STRATEGIES DISCOVER THEIR ERRORS
HOW INDUCTIVE INFERENCE STRATEGIES DISCOVER THEIR ERRORS
复制标题
DOI：
10.1006/inco.1995.1063
复制
发表时间：
1995-05-01
影响因子：
1
通讯作者：
WIEHAGEN, R
中科院分区：
文献类型：
--
作者：
FREIVALDS, R;KINBER, EB;WIEHAGEN, R
几个著名的归纳推理策略只有在发现它“可证明地错误分类”时才改变实际的假设，这是迄今为止看到的一个例子。这个概念在数学上是精确的，它的一般权力的特点。尽管它的力量，它表明，这种方法是不是普遍的权力。因此，假设被认为是“无法证明错误分类”的例子，这种方法的性质进行了研究。除其他外，事实证明，这种类型是相同的权力单调识别。然后，它表明，只有当一个无限数量的交替这些双重类型的假设是允许的，可以实现普遍的权力。最后，提出了一种通用的方法，使归纳推理策略，以验证其任何不正确的中间假设的不正确性。(C)出版社：Academic Press
Several well-known inductive inference strategies change the actual hypothesis only when they discover that it ''provably misclassifies'' an example seen so far. This notion is made mathematically precise, and its general power is characterized. In spite of its strength, it is shown that this approach is not of universal power. Consequently, hypotheses are considered which ''unprovably misclassify'' examples, and the properties of this approach are studied. Among others, it turns out that this type is of the same power as monotonic identification. Then it is shown that universal power can be achieved only when an unbounded number of alternations of these dual types of hypotheses is allowed. Finally, a universal method is presented, enabling an inductive inference strategy to verify the incorrectness of any of its incorrect intermediate hypotheses. (C) 1995 Academic Press, Inc.