Generating Correct Answers for Progressive Matrices Intelligence Tests
This work addresses a harder task in AI intelligence testing by generating answers from scratch, which is incremental as it builds on existing generative methods.
The paper tackles the problem of generating correct answers for Raven's Progressive Matrices intelligence tests without seeing multiple-choice options, using a neural model that combines generative techniques, and achieves competitive performance with state-of-the-art methods on multiple-choice tests.
Raven's Progressive Matrices are multiple-choice intelligence tests, where one tries to complete the missing location in a $3\times 3$ 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.