Log In Sign Up

Generating Correct Answers for Progressive Matrices Intelligence Tests

by   Niv Pekar, et al.

Raven's Progressive Matrices are multiple-choice intelligence tests, where one tries to complete the missing location in a 3× 3 grid of abstract images. Previous attempts to address this test have focused solely on selecting the right answer out of the multiple choices. In this work, we focus, instead, on generating a correct answer given the grid, without seeing the choices, which is a harder task, by definition. The proposed neural model combines multiple advances in generative models, including employing multiple pathways through the same network, using the reparameterization trick along two pathways to make their encoding compatible, a dynamic application of variational losses, and a complex perceptual loss that is coupled with a selective backpropagation procedure. Our algorithm is able not only to generate a set of plausible answers, but also to be competitive to the state of the art methods in multiple-choice tests.


page 1

page 2

page 3

page 4


Raven's Progressive Matrices Completion with Latent Gaussian Process Priors

Abstract reasoning ability is fundamental to human intelligence. It enab...

A Semantic-based Method for Unsupervised Commonsense Question Answering

Unsupervised commonsense question answering is appealing since it does n...

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

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

AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications

To automatically correct handwritten assignments, the traditional approa...

The Achievement of Higher Flexibility in Multiple Choice-based Tests Using Image Classification Techniques

In spite of the high accuracy of the existing optical mark reading (OMR)...

Hierarchical Rule Induction Network for Abstract Visual Reasoning

Abstract reasoning refers to the ability to analyze information, discove...