arXiv：cs.LG· Carl M. Kadie·· 3 小时前AI 评分17
如何量化构造性归纳、知识与噪声过滤对归纳学习的价值
Quantifying the Value of Constructive Induction, Knowledge, and Noise Filtering on Inductive Learning
AI 导读
论文提出一种新的学习度量"有效维度"（effective dimension），可经验估计并做平均情况预测，比 VC 维度更广泛适用于机器与人类学习研究。该度量在包括 Backpropagation 在内的多个学习系统上得到验证，并精确预测了特征构造系统 FRINGE 的收益，发现该收益随目标概念复杂度增加而下降。
正文
Abstract:Learning research, as one of its central goals, tries to measure, model, and understand how learning-problem properties affect average-case learning performance. For example, we would like to quantify the value of constructive induction, noise filtering, and background knowledge. This paper describes the effective dimension, a new learning measure that helps link problem properties to learning performance. Like the Vapnik-Chervonenkis (VC) dimension, the effective dimension is often in a simple linear relation with problem properties. Unlike the VC dimension, the effective dimension can be estimated empirically and makes average-case predictions. It is therefore more widely applicable to machine and human learning research. The measure is demonstrated on several learning systems including Backpropagation. Finally, the measure is used to precisely predict the benefit of using FRINGE, a feature construction system. The benefit is found to decrease as the complexity of the target concept increases.
| Comments: | 12 pages, including a modern cover note and the unchanged 11-page author manuscript from 1991. Extended author version of a paper published in Machine Learning Proceedings 1991 (ICML 1991), pp. 153-157. Deposited in arXiv in 2026 |
| Subjects: | Machine Learning (cs.LG) |
| ACM classes: | I.2.6 |
| Cite as: | arXiv:2610.02615 [cs.LG] |
| (or arXiv:2610.02615v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02615 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Machine Learning Proceedings 1991, Morgan Kaufmann, pp. 153-157 (1991) |
| Related DOI: | https://doi.org/10.1016/B978-1-55860-200-7.50034-9
DOI(s) linking to related resources |
Submission history
From: Carl Kadie [view email]
[v1]
Fri, 2 Oct 2026 00:14:56 UTC (118 KB)
来源：arXiv：cs.LG · arxiv.org