arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.00848cs.AI
收藏

基于描述网格模型和最小描述长度原则的ARC挑战方法的第一步

First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle

Univ Rennes(雷恩大学);CNRS(法国国家科学研究中心);IRISA(法国布列塔尼大区计算机与随机系统研究所)

Sébastien Ferré

摘要:

抽象和推理语料库(ARC)是弗朗索瓦·肖莱(François Chollet)最近推出的一种衡量人类和机器广泛智能的工具。这是非常具有挑战性的,Kaggle竞赛中最好的方法只能解决20%的任务,依靠蛮力搜索手工制作的转换链。在本文中,我们提出了第一步探索的方法的基础上描述网格模型和最小描述长度(MDL)的原则。网格模型描述网格的内容,并支持解析网格和生成网格。MDL原则用于指导寻找好的模型,即最压缩网格的模型。我们报告了我们一年多来的进展,改进了一般方法和模型。在400个训练任务中,我们的性能从5个增加到29个已解决的任务,每个任务仅使用30秒的计算时间。我们的方法不仅预测了输出网格,而且还输出了一个可理解的模型,并解释了模型是如何逐步构建的。

英文摘要:

The Abstraction and Reasoning Corpus (ARC) was recently introduced by François Chollet as a tool to measure broad intelligence in both humans and machines. It is very challenging, and the best approach in a Kaggle competition could only solve 20% of the tasks, relying on brute-force search for chains of hand-crafted transformations. In this paper, we present the first steps exploring an approach based on descriptive grid models and the Minimum Description Length (MDL) principle. The grid models describe the contents of a grid, and support both parsing grids and generating grids. The MDL principle is used to guide the search for good models, i.e. models that compress the grids the most. We report on our progress over a year, improving on the general approach and the models. Out of the 400 training tasks, our performance increased from 5 to 29 solved tasks, only using 30s computation time per task. Our approach not only predicts the output grids, but also outputs an intelligible model and explanations for how the model was incrementally built.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑