Achievable rates for pattern recognition: binary and Gaussian cases
暂无分享,去创建一个
Recently we presented information-theoretic bounds for the achievable rates of pattern recognition systems operating under data compression constraints. In this paper we improve on our previous inner bound, and report progress toward finding formulas for the achievable rate region boundaries in the special cases where the pattern data is either binary or Gaussian
[1] John W. Clark,et al. Image representation and pattern recognition in brains and machines , 2006 .
[2] Joseph A. O'Sullivan,et al. Towards an information theoretic framework for object recognition , 2004, International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings..
[3] Giuseppe Longo,et al. The information theory approach to communications , 1977 .