arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.07038cs.LGcs.AIcs.CCcs.ITmath.IT
收藏

有条件的教学规模

Conditional Teaching Size

Universidad de Castilla-La Mancha(卡斯蒂利亚-拉曼恰大学);Universitat Politècnica de València(瓦伦西亚理工大学)

Manuel Garcia-Piqueras, José Hernández-Orallo

摘要:

最近的机器教学研究探索了用通用语言表达的任何概念的教学。在这种组合的情况下,新的实验结果表明,存在数据教学集令人惊讶地短于概念描述本身。然而,这些显着的实验结果存在一个界限,通过教学规模和概念的复杂性,我们在这里进一步探讨。由于概念很少孤立地教授,我们研究了概念的最佳配置来教授给定的一组概念,其中首先获得的概念可以重新用于描述新的概念。这种有条件的教学规模的新概念揭示了新的见解,例如插入现象:某些先验知识产生更简单的兼容概念,增加了我们想要教授的概念的教学规模。这在条件柯尔莫哥洛夫复杂度中不会发生。此外,我们提供了一个算法,构建最佳的课程的基础上避免干预。本文给出了一系列的理论结果,包括他们的证明,并为今后的工作提出了一些方向。新的研究可能性在课程教学中的组成情景,现在是开放的探索。

英文摘要:

Recent research in machine teaching has explored the instruction of any concept expressed in a universal language. In this compositional context, new experimental results have shown that there exist data teaching sets surprisingly shorter than the concept description itself. However, there exists a bound for those remarkable experimental findings through teaching size and concept complexity that we further explore here. As concepts are rarely taught in isolation we investigate the best configuration of concepts to teach a given set of concepts, where those that have been acquired first can be reused for the description of new ones. This new notion of conditional teaching size uncovers new insights, such as the interposition phenomenon: certain prior knowledge generates simpler compatible concepts that increase the teaching size of the concept that we want to teach. This does not happen for conditional Kolmogorov complexity. Furthermore, we provide an algorithm that constructs optimal curricula based on interposition avoidance. This paper presents a series of theoretical results, including their proofs, and some directions for future work. New research possibilities in curriculum teaching in compositional scenarios are now wide open to exploration.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑