Related Experiment Video
Updated: Sep 20, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
Published on: July 5, 2024
Staged Self-Supervised Learning for Raven Progressive Matrices
None:
This study presents and investigates abstract compositional transformers (ACTs), a class of deep learning (DL) architectures based on the transformer blueprint, designed to handle abstract reasoning tasks that require completing spatial visual patterns. We combine ACTs with choice-making modules and apply them to Raven progressive matrices (RPMs), logical puzzles that require selecting the correct image from the available answers. We devise a number of ACT variants, train them in several modes and with additional augmentations, subject them to ablations, demonstrate their data scalability, and analyze their behavior and latent representations that emerged in the process. Using self-supervision allows us to successfully train ACTs on relatively small training sets, mitigate several biases identified in RPMs in past studies, and achieve SotA results on the two most popular RPM benchmarks.
Related Concept Videos
Observational Learning
Associative Learning
Classical conditioning, also known...
Introduction to Learning
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Purposive Learning
Multi-input and Multi-variable systems
In the absence...

