Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
This addresses the problem of understanding brain organization for neuroscientists and AI researchers, but it is incremental as it builds on existing supervised approaches like TDANN.
The paper tackled modeling category-selective cortical regions like the Fusiform Face Area by using a Topographic Variational Autoencoder in an unsupervised manner, resulting in spatially dense neural clusters selective to faces, bodies, and places as shown through visualized Cohen's d metric maps.
Category-selectivity in the brain describes the observation that certain spatially localized areas of the cerebral cortex tend to respond robustly and selectively to stimuli from specific limited categories. One of the most well known examples of category-selectivity is the Fusiform Face Area (FFA), an area of the inferior temporal cortex in primates which responds preferentially to images of faces when compared with objects or other generic stimuli. In this work, we leverage the newly introduced Topographic Variational Autoencoder to model the emergence of such localized category-selectivity in an unsupervised manner. Experimentally, we demonstrate our model yields spatially dense neural clusters selective to faces, bodies, and places through visualized maps of Cohen's d metric. We compare our model with related supervised approaches, namely the Topographic Deep Artificial Neural Network (TDANN) of Lee et al., and discuss both theoretical and empirical similarities. Finally, we show preliminary results suggesting that our model yields a nested spatial hierarchy of increasingly abstract categories, analogous to observations from the human ventral temporal cortex.