Inductive Inference of an Approximate Concept from Positive Data
Inductive Inference of an Approximate Concept from Positive Data
复制标题
从正面数据归纳推断近似概念
DOI：
10.1007/3-540-58520-6_85
复制
发表时间：
1994
期刊：
影响因子：
--
通讯作者：
Yasuhito Mukouchi
中科院分区：
文献类型：
--
作者：
Yasuhito Mukouchi
在普通的学习范式中，一个目标概念，其示例被馈送到一个推理机，被假定属于一个假设空间，这是预先给定的。然而，如果我们想让一个推理机去推理或发现一个未知的规则来解释从科学实验中得到的例子或数据，那么这个假设就不合适了。Mukouchi和Arikawa在他们的前一篇论文中讨论了假设空间的可反驳性和可推理性。本文将极小概念作为假设空间中的一个近似概念，讨论了目标概念的极小概念不属于假设空间的可推理性。也就是说，如果假设空间内存在目标概念的最小概念，则我们强制推理机收敛到目标概念的最小概念。我们还表明，有一些丰富的假设空间，是最低限度地推断从积极的数据。
In ordinary learning paradigm, a target concept, whose examples are fed to an inference machine, is assumed to belong to a hypothesis space which is given in advance. However this assumption is not appropriate, if we want an inference machine to infer or to discover an unknown rule which explains examples or data obtained from scientific experiments.In their previous paper, Mukouchi and Arikawa discussed both refutability and inferability of a hypothesis space from examples. In this paper, we take a minimal concept as an approximate concept within a hypothesis space, and discuss inferability of a minimal concept of the target concept which may not belong to the hypothesis space. That is, we force an inference machine to converge to a minimal concept of the target concept, if there is a minimal concept of the target concept within the hypothesis space. We also show that there are some rich hypothesis spaces that are minimally inferable from positive data.