A simple neural network module for relational reasoning
A simple neural network module for relational reasoning
复制标题
DOI：
--
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
Adam Santoro;David Raposo;D. Barrett;Mateusz Malinowski;Razvan Pascanu;P. Battaglia;T. Lillicrap
中科院分区：
文献类型：
--
作者：
Adam Santoro;David Raposo;D. Barrett;Mateusz Malinowski;Razvan Pascanu;P. Battaglia;T. Lillicrap
关系推理是通用智能行为的核心组成部分，但已证明神经网络难以学习。在本文中，我们描述了如何使用关系网络（RNs）作为一个简单的即插即用模块来解决根本上依赖于关系推理的问题。我们在三个任务上测试了添加关系网络的网络：使用一个具有挑战性的数据集CLEVR进行视觉问答，在该任务上我们取得了最先进的、超越人类的性能；使用bAbI任务集进行基于文本的问答；以及对动态物理系统进行复杂推理。然后，使用一个名为Sort-of - CLEVR的精选数据集，我们表明强大的卷积网络不具备解决关系问题的通用能力，但在添加关系网络后可以获得这种能力。我们的工作展示了配备关系网络模块的深度学习架构如何能够隐式地发现并学会对实体及其关系进行推理。
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning. We tested RN-augmented networks on three tasks: visual question answering using a challenging dataset called CLEVR, on which we achieve state-of-the-art, super-human performance; text-based question answering using the bAbI suite of tasks; and complex reasoning about dynamic physical systems. Then, using a curated dataset called Sort-of-CLEVR we show that powerful convolutional networks do not have a general capacity to solve relational questions, but can gain this capacity when augmented with RNs. Our work shows how a deep learning architecture equipped with an RN module can implicitly discover and learn to reason about entities and their relations.