Solving Raven's Progressive Matrices with Multi-Layer Relation Networks

by   Marius Jahrens, et al.

Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.


page 1

page 2

page 3

page 4


Multi-layer Relation Networks

Relational Networks (RN) as introduced by Santoro et al. (2017) have dem...

Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices

Abstract visual reasoning (AVR) domain encompasses problems solving whic...

Recurrent Relational Networks for Complex Relational Reasoning

Humans possess an ability to abstractly reason about objects and their i...

Pairwise Relations Discriminator for Unsupervised Raven's Progressive Matrices

Abstract reasoning is a key indicator of intelligence. The ability to hy...

Abstract Diagrammatic Reasoning with Multiplex Graph Networks

Abstract reasoning, particularly in the visual domain, is a complex huma...

Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices

We introduce algebraic machine reasoning, a new reasoning framework that...

Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks

Current successes of machine learning architectures are based on computa...

Please sign up or login with your details

Forgot password? Click here to reset