.png){kind=icon}
返回
Hypothesizing an algorithm from one example: the role of specificity
.png){kind=icon}
OA
AI
DOI：10.1098/rsta.2022.0046.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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'.
Keyword:
program synthesis
Bayesian machine learning
logic learning
期刊
P
IF:
3.7
论文数:
7.8K
被引数:
2.8W
机构
引用论文
分享收藏分享收藏Exploring variations of hexabromocyclododecane concentrations in riverine sediments along the River Medway, UK探索英国梅德韦河河流沉积物中六溴环十二烷浓度的变化OAAI
OAAI分享收藏Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited.png)
MACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏Skyrmion-electronics: writing, deleting, reading and processing magnetic skyrmions toward spintronic applicationsSkyrmion-电子学: 用于自旋电子应用的写入，删除，读取和处理磁性SkyrmionOAAI
OAAI分享收藏
查看更多内容