A simple neural network module for relational reasoning

06/05/2017
by   Adam Santoro, et al.
0

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.

READ FULL TEXT
research
01/25/2018

Finding ReMO (Related Memory Object): A Simple Neural Architecture for Text based Reasoning

To solve the text-based question and answering task that requires relati...
research
11/21/2017

Recurrent Relational Networks for Complex Relational Reasoning

Humans possess an ability to abstractly reason about objects and their i...
research
05/30/2019

What Can Neural Networks Reason About?

Neural networks have successfully been applied to solving reasoning task...
research
09/07/2019

Relationships from Entity Stream

Relational reasoning is a central component of intelligent behavior, but...
research
06/12/2018

A Question-Answering framework for plots using Deep learning

Deep Learning has managed to push boundaries in a wide variety of tasks....
research
05/27/2021

Relational Gating for "What If" Reasoning

This paper addresses the challenge of learning to do procedural reasonin...
research
02/09/2018

Not-So-CLEVR: Visual Relations Strain Feedforward Neural Networks

The robust and efficient recognition of visual relations in images is a ...

Please sign up or login with your details

Forgot password? Click here to reset