“Artiphysiology” reveals V4-like shape tuning in a deep network trained for image classification
Deep convolutional neural networks (CNNs) provide a potentially rich source of insight for understanding mid-level visual processing in the primate cerebral cortex. Taking the approach of an electrophysiologist to characterizing single CNN units, we found that many units exhibit translation-invariant boundary curvature selectivity approaching that of the best neurons in the mid-level visual area V4.
For some of these V4-like units, particularly in the middle layers, the natural images that drove them best were also qualitatively consistent with selectivity for object boundaries. Our results identify a novel image-computable model for V4 boundary curvature selectivity and suggest that such a representation may begin to emerge within the middle layers of an artificial network trained for image categorization, even though boundary information was not provided during training. This raises the general possibility that single-unit feature selectivity learned in CNNs may become a valuable guide for understanding sensory cortex.
Date: 23 August 2018, 15:00 (Thursday, 18th week, Trinity 2018)
Venue: Sherrington Library, off Parks Road OX1 3PT
Speaker: Prof Wyeth Bair (University of Washington)
Organising department: Department of Physiology, Anatomy and Genetics (DPAG)
Host: Progessor Andrew Parker (Department of Physiology, Anatomy and Genetics)
Part of: Neuroscience Theme Guest Speakers (DPAG)
Booking required?: Not required
Audience: Members of the University only
Editor: Isabella Renehan