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:
影响因子:
--
通讯作者:
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
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.
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
影响因子:
--
作者:
Lubin, Justin;Collins, Nick;Omar, Cyrus;Chugh, Ravi
通讯作者:
Chugh, Ravi