An Explicitly Relational Neural Network Architecture

05/24/2019
by   Murray Shanahan, et al.
13

With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data. In order to evaluate and analyse the architecture, we introduce a family of simple visual relational reasoning tasks of varying complexity. We show that the proposed architecture, when pre-trained on a curriculum of such tasks, learns to generate reusable representations that better facilitate subsequent learning on previously unseen tasks when compared to a number of baseline architectures. The workings of a successfully trained model are visualised to shed some light on how the architecture functions.

READ FULL TEXT

page 4

page 7

page 14

research
07/12/2020

Relational-Grid-World: A Novel Relational Reasoning Environment and An Agent Model for Relational Information Extraction

Reinforcement learning (RL) agents are often designed specifically for a...
research
06/18/2018

Modularity Matters: Learning Invariant Relational Reasoning Tasks

We focus on two supervised visual reasoning tasks whose labels encode a ...
research
11/02/2020

Chess2vec: Learning Vector Representations for Chess

We conduct the first study of its kind to generate and evaluate vector r...
research
06/01/2021

Learning Representations for Sub-Symbolic Reasoning

Neuro-symbolic methods integrate neural architectures, knowledge represe...
research
01/31/2019

Learning to Make Analogies by Contrasting Abstract Relational Structure

Analogical reasoning has been a principal focus of various waves of AI r...
research
10/17/2016

Learning and Transfer of Modulated Locomotor Controllers

We study a novel architecture and training procedure for locomotion task...
research
09/02/2023

Discovering Predictive Relational Object Symbols with Symbolic Attentive Layers

In this paper, we propose and realize a new deep learning architecture f...

Please sign up or login with your details

Forgot password? Click here to reset