Neural-guided, Bidirectional Program Search for Abstraction and Reasoning

Neural-guided, Bidirectional Program Search for Abstraction and Reasoning
复制标题

用于抽象和推理的神经引导双向程序搜索

DOI:
--
复制
发表时间:
2021
期刊:
International Workshop on Complex Networks & Their Applications
影响因子:
--
通讯作者:
S. Chin
S. Chin
中科院分区:
--
文献类型:
--
作者:
Simon Alford;Anshul Gandhi;Akshay Rangamani;Andrzej Banburski;Tony Wang;Sylee Dandekar;John Chin;T. Poggio;S. Chin

文献摘要

参考文献

被引文献

相似文献

当今人工智能研究面临的挑战之一是设计能够利用系统推理来概括新任务的系统。抽象和推理语料库(ARC)通过一组视觉推理任务来衡量这种能力。在本文中,我们报告了ARC的渐进式进展,并为两种不基于蛮力搜索的抽象和推理方法奠定了基础。我们首先应用现有的程序合成系统称为DreamCoder创建符号抽象的任务解决到目前为止,并显示它如何使解决越来越具有挑战性的ARC任务。其次,我们设计了一个推理算法的动机,人类的方式接近ARC。我们的算法构造了一个搜索图,并在此图结构的原因,发现任务的解决方案。更具体地说,我们扩展现有的执行指导的程序合成方法与演绎推理的基础上的功能逆语义,使神经指导的双向搜索算法。我们证明了该算法的有效性三个域:ARC,24场比赛的任务,和一个“双加”算术难题。
One of the challenges facing artificial intelligence research today is designing systems capable of utilizing systematic reasoning to generalize to new tasks. The Abstraction and Reasoning Corpus (ARC) measures such a capability through a set of visual reasoning tasks. In this paper we report incremental progress on ARC and lay the foundations for two approaches to abstraction and reasoning not based in brute-force search. We first apply an existing program synthesis system called DreamCoder to create symbolic abstractions out of tasks solved so far, and show how it enables solving of progressively more challenging ARC tasks. Second, we design a reasoning algorithm motivated by the way humans approach ARC. Our algorithm constructs a search graph and reasons over this graph structure to discover task solutions. More specifically, we extend existing execution-guided program synthesis approaches with deductive reasoning based on function inverse semantics to enable a neural-guided bidirectional search algorithm. We demonstrate the effectiveness of the algorithm on three domains: ARC, 24-Game tasks, and a 'double-and-add' arithmetic puzzle.
DOI: --
发表时间: 2018-03
期刊: Energies
影响因子: 3.2
作者:
Lazar Valkov;Dipak Chaudhari;Akash Srivastava;Charles Sutton;Swarat Chaudhuri
通讯作者: Lazar Valkov;Dipak Chaudhari;Akash Srivastava;Charles Sutton;Swarat Chaudhuri
DOI: --
发表时间: 2018-09
期刊: --
影响因子: --
作者:
S. McAleer;Forest Agostinelli;A. Shmakov;P. Baldi
通讯作者: S. McAleer;Forest Agostinelli;A. Shmakov;P. Baldi
通过实时双向评估进行程序草图绘制
DOI: 10.1145/3408991
发表时间: 2020
影响因子: --
作者:
Lubin, Justin;Collins, Nick;Omar, Cyrus;Chugh, Ravi
通讯作者: Chugh, Ravi