Log In Sign Up

Raven's Progressive Matrices Completion with Latent Gaussian Process Priors

by   Fan Shi, et al.

Abstract reasoning ability is fundamental to human intelligence. It enables humans to uncover relations among abstract concepts and further deduce implicit rules from the relations. As a well-known abstract visual reasoning task, Raven's Progressive Matrices (RPM) are widely used in human IQ tests. Although extensive research has been conducted on RPM solvers with machine intelligence, few studies have considered further advancing the standard answer-selection (classification) problem to a more challenging answer-painting (generating) problem, which can verify whether the model has indeed understood the implicit rules. In this paper we aim to solve the latter one by proposing a deep latent variable model, in which multiple Gaussian processes are employed as priors of latent variables to separately learn underlying abstract concepts from RPMs; thus the proposed model is interpretable in terms of concept-specific latent variables. The latent Gaussian process also provides an effective way of extrapolation for answer painting based on the learned concept-changing rules. We evaluate the proposed model on RPM-like datasets with multiple continuously-changing visual concepts. Experimental results demonstrate that our model requires only few training samples to paint high-quality answers, generate novel RPM panels, and achieve interpretability through concept-specific latent variables.


page 1

page 2

page 3

page 4


Compositional Law Parsing with Latent Random Functions

Human cognition has compositionality. We understand a scene by decomposi...

Generating Correct Answers for Progressive Matrices Intelligence Tests

Raven's Progressive Matrices are multiple-choice intelligence tests, whe...

A Memory-Augmented Neural Network Model of Abstract Rule Learning

Human intelligence is characterized by a remarkable ability to infer abs...

Pairwise Relations Discriminator for Unsupervised Raven's Progressive Matrices

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

Effective Abstract Reasoning with Dual-Contrast Network

As a step towards improving the abstract reasoning capability of machine...

Abstract Reasoning via Logic-guided Generation

Abstract reasoning, i.e., inferring complicated patterns from given obse...

Visual-Imagery-Based Analogical Construction in Geometric Matrix Reasoning Task

Raven's Progressive Matrices is a family of classical intelligence tests...

Code Repositories


Research on deep structured latent variable models

view repo