Hypothesizing an algorithm from one example: the role of specificity.
Hypothesizing an algorithm from one example: the role of specificity.
复制标题
DOI：
10.1098/rsta.2022.0046
复制
发表时间：
2023-07-24
期刊：
影响因子：
5
通讯作者：
FREng, S. H. Muggleton
中科院分区：
文献类型：
--
作者：
FREng, S. H. Muggleton
统计机器学习通常通过使用数以万计的例子来实现高精度的模型。相比之下，儿童和成年人通常都是从一个或少数实例中学习新概念。人类学习的高数据效率并不容易用机器学习的标准正式框架来解释，包括Gold的极限学习框架和Valiant的可能近似正确（PAC）模型。本文探讨了人类和机器学习之间的这种明显差异可以通过考虑涉及特异性偏好与程序最小化相结合的算法来调和的方法。它展示了如何使用基于证书识别的分层搜索和下推自动机来有效地实现这一点，以支持假设的紧凑表达的最大效率算法。一个名为DeepLog的新系统的早期结果表明，这种方法可以支持从单个示例中高效地自顶向下构建相对复杂的逻辑程序。本文是“认知人工智能”讨论会议的一部分。
Statistical machine learning usually achieves high-accuracy models by employing tens of thousands of examples. By contrast, both children and adult humans typically learn new concepts from either one or a small number of instances. The high data efficiency of human learning is not easily explained in terms of standard formal frameworks for machine learning, including Gold’s learning-in-the-limit framework and Valiant’s probably approximately correct (PAC) model. This paper explores ways in which this apparent disparity between human and machine learning can be reconciled by considering algorithms involving a preference for specificity combined with program minimality. It is shown how this can be efficiently enacted using hierarchical search based on identification of certificates and push-down automata to support hypothesizing compactly expressed maximal efficiency algorithms. Early results of a new system called DeepLog indicate that such approaches can support efficient top-down construction of relatively complex logic programs from a single example. This article is part of a discussion meeting issue ‘Cognitive artificial intelligence’.
登录
查看更多内容
影响因子：
3.6
作者：
GOULDEN, R;NATION, P;READ, J
通讯作者：
READ, J
影响因子：
7.5
作者：
Muggleton, Stephen H.;Lin, Dianhuan;Tamaddoni-Nezhad, Alireza
通讯作者：
Tamaddoni-Nezhad, Alireza
DOI：
10.1109/tpami.2006.79
发表时间：
2006-04-01
影响因子：
23.6
作者：
Li, FF;Fergus, R;Perona, P
通讯作者：
Perona, P
影响因子：
7.5
作者：
Cropper, Andrew;Dumancic, Sebastijan;Muggleton, Stephen H.
通讯作者：
Muggleton, Stephen H.
影响因子：
--
作者：
GOLD, EM
通讯作者：
GOLD, EM