Technical Program

Paper Detail

Paper: PS-2A.15
Session: Poster Session 2A
Location: Symphony/Overture
Session Time: Friday, September 7, 17:15 - 19:15
Presentation Time:Friday, September 7, 17:15 - 19:15
Presentation: Poster
Paper Title: Topographic Deep Artificial Neural Networks (TDANNs) predict face selectivity topography in primate inferior temporal (IT) cortex
Manuscript:  Click here to view manuscript
Authors: Hyodong Lee, James DiCarlo, Massachusetts Institute of Technology, United States
Abstract: Deep convolutional neural networks are biologically driven models that resemble the hierarchical structure of primate visual cortex and are the current best predictors of the neural responses measured along the ventral stream. However, the networks lack topographic properties that are present in the visual cortex, such as orientation maps in primary visual cortex and category- selective maps in inferior temporal (IT) cortex. In this work, the minimum wiring cost constraint was approximated as an additional learning rule in order to generate topographic maps of the networks. We found that our topographic deep artificial neural networks (ANNs) can reproduce the category selectivity maps of the primate IT cortex.