Learning a visual representation by maximizing manifold capacity
Thomas Yerxa, Yilun Kuang, Eero Simoncelli, SueYeon Chung · COSYNE 2023
Biological visual systems learn complex representations of the world that support a wide range of cognitive behaviors without using a large number of labelled examples. The efficient coding hypothesis suggests that this is accomplished by adapting the sensory representation to the statistics of the input signal, i.e. in a way that facilitates redundancy reduction. Visual signals have several clear sources of redundancy. They evolve slowly in time, since temporally adjacent inputs typically correspond to different views of the same scene, which in turn are usually more similar than views of dis
Fri, Mar 10, 2023