Dimensionality reduction may be the wrong approach to understanding neural representations. Our new paper shows that across human visual cortex, dimensionality is unbounded and scales with dataset size—we show this across nearly four orders of magnitude. https://t.co/SuGhRg7L5F
Can we gain a deep understanding of neural representations through dimensionality reduction? Our new work shows that the visual representations of the human brain need to be understood in high dimensions. w/ @RajThrowaway42 & Brice Ménard. https://t.co/mY2TnHj4Et
Why do varied DNN designs yield equally good models of human vision? Our preprint with @michaelfbonner shows that diverse DNNs represent images with a shared set of latent dimensions, and these shared dimensions turn out to also be the most brain-aligned.
https://t.co/vtOOYHQb47
The invariance of these representations implies that they are not primarily governed by the details of a DNN’s design but instead by more general principles of natural image representation in vision systems.
New paper out in @PLOSCompBiol. The best deep neural network models of visual cortex do not reduce representations to low-dimensional manifolds—instead, they benefit from high-dimensionality. Led by a fantastic student, @EricElmoznino. https://t.co/PPIuP6vaeN