Cognitive Neural Architecture Search Reveals Hierarchical Entailment
This work addresses the fundamental question of hierarchical structure in primate visual processing for computational cognitive neuroscience, offering a novel framework to reduce reliance on manually designed networks.
The researchers tackled the problem of understanding brain hierarchy in visual processing by using evolutionary neural architecture search to optimize convolutional networks for brain-alignment, finding that these models with random weights achieved brain-alignment scores surpassing pretrained classification models and that architectures optimized for late ventral regions became competitive classification models after supervised training.
Recent research has suggested that the brain is more shallow than previously thought, challenging the traditionally assumed hierarchical structure of the ventral visual pathway. Here, we demonstrate that optimizing convolutional network architectures for brain-alignment via evolutionary neural architecture search results in models with clear representational hierarchies. Despite having random weights, the identified models achieve brain-alignment scores surpassing even those of pretrained classification models - as measured by both regression and representational similarity analysis. Furthermore, through traditional supervised training, architectures optimized for alignment with late ventral regions become competitive classification models. These findings suggest that hierarchical structure is a fundamental mechanism of primate visual processing. Finally, this work demonstrates the potential of neural architecture search as a framework for computational cognitive neuroscience research that could reduce the field's reliance on manually designed convolutional networks.