Learning to Make Analogies by Contrasting Abstract Relational Structure

by   Felix Hill, et al.

Analogical reasoning has been a principal focus of various waves of AI research. Analogy is particularly challenging for machines because it requires relational structures to be represented such that they can be flexibly applied across diverse domains of experience. Here, we study how analogical reasoning can be induced in neural networks that learn to perceive and reason about raw visual data. We find that the critical factor for inducing such a capacity is not an elaborate architecture, but rather, careful attention to the choice of data and the manner in which it is presented to the model. The most robust capacity for analogical reasoning is induced when networks learn analogies by contrasting abstract relational structures in their input domains, a training method that uses only the input data to force models to learn about important abstract features. Using this technique we demonstrate capacities for complex, visual and symbolic analogy making and generalisation in even the simplest neural network architectures.


Relational reasoning and generalization using non-symbolic neural networks

Humans have a remarkable capacity to reason about abstract relational st...

What Can Neural Networks Reason About?

Neural networks have successfully been applied to solving reasoning task...

Abstract Reasoning with Distracting Features

Abstraction reasoning is a long-standing challenge in artificial intelli...

Abstractors: Transformer Modules for Symbolic Message Passing and Relational Reasoning

A framework is proposed that casts relational learning in terms of trans...

Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review

Advocates for Neuro-Symbolic AI (NeSy) assert that combining deep learni...

An Explicitly Relational Neural Network Architecture

With a view to bridging the gap between deep learning and symbolic AI, w...

Measuring abstract reasoning in neural networks

Whether neural networks can learn abstract reasoning or whether they mer...

Please sign up or login with your details

Forgot password? Click here to reset