Relational recurrent neural networks

06/05/2018
by   Adam Santoro, et al.
2

Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to perform complex relational reasoning with the information they remember. Here, we first confirm our intuitions that standard memory architectures may struggle at tasks that heavily involve an understanding of the ways in which entities are connected -- i.e., tasks involving relational reasoning. We then improve upon these deficits by using a new memory module -- a Relational Memory Core (RMC) -- which employs multi-head dot product attention to allow memories to interact. Finally, we test the RMC on a suite of tasks that may profit from more capable relational reasoning across sequential information, and show large gains in RL domains (e.g. Mini PacMan), program evaluation, and language modeling, achieving state-of-the-art results on the WikiText-103, Project Gutenberg, and GigaWord datasets.

READ FULL TEXT
research
11/21/2017

Recurrent Relational Networks for Complex Relational Reasoning

Humans possess an ability to abstractly reason about objects and their i...
research
05/23/2018

Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module

During the last years, there has been a lot of interest in achieving som...
research
11/01/2018

SARN: Relational Reasoning through Sequential Attention

This paper proposes an attention module augmented relational network cal...
research
06/15/2023

Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding

Dual-task dialog language understanding aims to tackle two correlative d...
research
02/10/2020

Self-Assttentive Associative Memory

Heretofore, neural networks with external memory are restricted to singl...
research
10/11/2019

R-SQAIR: Relational Sequential Attend, Infer, Repeat

Traditional sequential multi-object attention models rely on a recurrent...
research
02/10/2020

Self-Attentive Associative Memory

Heretofore, neural networks with external memory are restricted to singl...

Please sign up or login with your details

Forgot password? Click here to reset