Brain-optimized deep neural network models of human visual areas learn non-hierarchical representations

Citations Over TimeTop 10% of 2023 papers

Abstract

Deep neural networks (DNNs) optimized for visual tasks learn representations that align layer depth with the hierarchy of visual areas in the primate brain. One interpretation of this finding is that hierarchical representations are necessary to accurately predict brain activity in the primate visual system. To test this interpretation, we optimized DNNs to directly predict brain activity measured with fMRI in human visual areas V1-V4. We trained a single-branch DNN to predict activity in all four visual areas jointly, and a multi-branch DNN to predict each visual area independently. Although it was possible for the multi-branch DNN to learn hierarchical representations, only the single-branch DNN did so. This result shows that hierarchical representations are not necessary to accurately predict human brain activity in V1-V4, and that DNNs that encode brain-like visual representations may differ widely in their architecture, ranging from strict serial hierarchies to multiple independent branches.

Related Papers

• → New developments on the Encyclopedia of DNA Elements (ENCODE) data portal(2019)1,073 cited
• → Using the ENCODE Resource for Functional Annotation of Genetic Variants(2015)32 cited
• → Extrapolating ENCODE data to the whole human genome(2008)2 cited
• The Study of OCDMA Encode/Decode Using Multilayer Films(2001)
• The ENCODE Project Decoded(2012)