A performance-optimized model of neural responses across the ventral visual stream
Darren Seibert, Daniel Yamins, Diego Ardila, Ha Hong, James J. DiCarlo, Justin L. Gardner
This paper builds a deep convolutional neural network optimized for object recognition and shows its hierarchical representations align with human ventral visual stream areas from V1 to LOC.
bioRxiv · Jan 12, 2016 · PreprintNeuroscience