17 citations · 24 across the 8 of their papers we have counts for
8 papers
A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processing
Yuan Yang, Deepayan Sanyal, James Ainooson +3
We introduce a new neural architecture for solving visual abstract reasoning tasks inspired by human cognition, specifically by observations that human abstract reasoning often int…
A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Play
Deepayan Sanyal, Joel Michelson, Yuan Yang +2
Research in child development has shown that embodied experience handling physical objects contributes to many cognitive abilities, including visual learning. One characteristic of…
Deep Non-Monotonic Reasoning for Visual Abstract Reasoning Tasks
Yuan Yang, Deepayan Sanyal, Joel Michelson +2
While achieving unmatched performance on many well-defined tasks, deep learning models have also been used to solve visual abstract reasoning tasks, which are relatively less well-…
A Neurodiversity-Inspired Solver for the Abstraction \& Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis
James Ainooson, Deepayan Sanyal, Joel P. Michelson +2
Core knowledge about physical objects -- e.g., their permanency, spatial transformations, and interactions -- is one of the most fundamental building blocks of biological intellige…
Automatic Item Generation of Figural Analogy Problems: A Review and Outlook
Yuan Yang, Deepayan Sanyal, Joel Michelson +2
Figural analogy problems have long been a widely used format in human intelligence tests. In the past four decades, more and more research has investigated automatic item generatio…
Variable-Viewpoint Representations for 3D Object Recognition
Tengyu Ma, Joel Michelson, James Ainooson +3
For the problem of 3D object recognition, researchers using deep learning methods have developed several very different input representations, including "multi-view" snapshots take…