Abstract visual reasoning (AVR) domain encompasses problems solving which requires the ability to reason about relations among entities present in a given scene. While humans, generally, solve AVR tasks in a "natural" way, even without prior experience, this type of problems has proven difficult for current machine learning systems. The paper summarises recent progress in applying deep learning methods to solving AVR problems, as a proxy for studying machine intelligence. We focus on the most common type of AVR tasks -- the Raven's Progressive Matrices (RPMs) -- and provide a comprehensive review of the learning methods and deep neural models applied to solve RPMs, as well as, the RPM benchmark sets. Performance analysis of the state-of-the-art approaches to solving RPMs leads to formulation of certain insights and remarks on the current and future trends in this area. We conclude the paper by demonstrating how real-world problems can benefit from the discoveries of RPM studies.
翻译:抽象直观推理(AVR)领域包括解决问题,这要求人们能够了解在特定场景中存在的实体之间的关系。一般而言,人类以“自然”的方式解决AVR任务,即使没有以往的经验,但对于目前的机器学习系统来说,这类问题证明是困难的。文件总结了最近在应用深层次学习方法解决AVR问题方面取得的进展,作为研究机器情报的替代物。我们侧重于AVR最常见的任务类型,即Raven's Progresulal Macrices(RPMs) -- -- 并全面审查了用于解决RPM的学习方法和深层神经模型以及RPM基准集。对解决RPM的先进方法的绩效分析导致对该领域当前和未来趋势的某些见解和评论。我们通过展示RPM研究发现如何有益于现实世界问题来结束这份文件。