Towards an information theoretic framework for object recognition
Michael Brandon Westover, Joseph A. O’Sullivan · 2004
We propose a model for rate-constrained pattern recognition problems, and present single-letter information bounds governing the conditions under which asymptotically error-free recognition is possible. The bounds depend on the statistics of the training and testing data, the number of pattern classes, and the rates of the codes used by the recognition system to internalize the data.