.png){kind=icon}
返回
DreamCoder: growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
.png){kind=icon}
OA
AI
DOI：10.1098/rsta.2022.0050.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Expert problem-solving is driven by powerful languages for thinking about problems and their solutions. Acquiring expertise means learning these languages-systems of concepts, alongside the skills to use them. We present DreamCoder, a system that learns to solve problems by writing programs. It builds expertise by creating domain-specific programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages. A 'wake-sleep' learning algorithm alternately extends the language with new symbolic abstractions and trains the neural network on imagined and replayed problems. DreamCoder solves both classic inductive programming tasks and creative tasks such as drawing pictures and building scenes. It rediscovers the basics of modern functional programming, vector algebra and classical physics, including Newton's and Coulomb's laws. Concepts are built compositionally from those learned earlier, yielding multilayered symbolic representations that are interpretable and transferrable to new tasks, while still growing scalably and flexibly with experience.This article is part of a discussion meeting issue 'Cognitive artificial intelligence'.
Keyword:
program synthesis
expertise
Bayesian program learning
期刊
P
IF:
3.7
论文数:
7.8K
被引数:
2.8W
机构
引用论文
Electron transfer reaction of cytochrome C3 at pyrolytic graphite electrodesC3细胞色素在热解石墨电极上的电子转移反应
PREAI
分享收藏分享收藏Polarographic behavior of uranium(VI) in malonic acid media determination of uranium in plutonium丙二酸介质中铀(VI)的极谱行为及其在钚中铀的测定
PREAI
分享收藏Synthesizing theories of human language with Bayesian program induction.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏分享收藏Cognitive Predictors of Obsessive–Compulsive Symptoms in Adolescence: A Preliminary Investigation
PREAI
分享收藏
查看更多内容