Solving Raven's Progressive Matrices with Multi-Layer Relation Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
RelationRelational ReasoningSimilar Papers 제목 키워드 기반
Visual-Imagery-Based Analogical Construction in Geometric Matrix Reasoning Task
Raven's Progressive Matrices is a family of classical intelligence tests that have been widely used in both research and clinical settings. There have been many exciting efforts in AI communities to computationally model…
Solving Raven's Progressive Matrices with Neural Networks
Raven's Progressive Matrices (RPM) have been widely used for Intelligence Quotient (IQ) test of humans. In this paper, we aim to solve RPM with neural networks in both supervised and unsupervised manners. First, we inves…
Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
We introduce algebraic machine reasoning, a new reasoning framework that is well-suited for abstract reasoning. Effectively, algebraic machine reasoning reduces the difficult process of novel problem-solving to routine a…
Visual ReasoningComputational Models of Solving Raven's Progressive Matrices: A Comprehensive Introduction
As being widely used to measure human intelligence, Raven's Progressive Matrices (RPM) tests also pose a great challenge for AI systems. There is a long line of computational models for solving RPM, starting from 1960s, …
PhilosophyA Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices
Neither deep neural networks nor symbolic AI alone has approached the kind of intelligence expressed in humans. This is mainly because neural networks are not able to decompose joint representations to obtain distinct ob…
Logical Reasoning