发表机构
University of Illinois at Urbana-Champaign; Microsoft Research（伊利诺伊大学厄巴纳-香槟分校; 微软研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出有效维度这一新学习度量，连接问题属性与学习性能，可经验估计并做平均预测，用于量化构造归纳、噪声过滤和背景知识的价值，并精确预测FRINGE特征构造系统的收益随目标概念复杂度增加而减少。
AI 中文摘要
学习研究的一个核心目标是测量、建模和理解学习问题属性如何影响平均情况下的学习性能。例如，我们希望量化构造归纳、噪声过滤和背景知识的价值。本文描述了有效维度（effective dimension），这是一种新的学习度量，有助于将问题属性与学习性能联系起来。与Vapnik-Chervonenkis（VC）维度类似，有效维度通常与问题属性呈简单的线性关系。与VC维度不同，有效维度可以通过经验估计，并能做出平均情况下的预测。因此，它更广泛地适用于机器学习和人类学习研究。该度量在包括反向传播（Backpropagation）在内的多个学习系统上得到了验证。最后，该度量被用于精确预测使用FRINGE（一种特征构造系统）的收益。研究发现，随着目标概念复杂度的增加，这种收益会减少。
英文摘要
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.
Comments12 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
Journal refMachine Learning Proceedings 1991, Morgan Kaufmann, pp. 153-157 (1991)
DOI：10.1016/B978-1-55860-200-7.50034-9
